© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12167
    Prev
    Next
    INDEX
    Explanations

    text from software licenses

    oai_token-act-pair · gemini-2.0-flash

    legal disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    •the_software_is_provided_"as:8f2232d9-1f50-5497-9669-5fe230633d9c:gemma-2-2b:gemmascope-transcoder-16k
    Top frequency features for prompt
    •the_software_is_provided_"as:a019a833-837d-5856-ba72-b7f81f2e9c66:gemma-2-2b:gemmascope-transcoder-16k
    Top frequency features for prompt
    •the_software_and_any_accompanying:1f572b82-898a-54ac-bb18-1f0b7cadf481:gemma-2-2b:gemmascope-transcoder-16k
    Top frequency features for prompt
    •the_software_and_any_accompanying:12df250e-58b2-5943-bb28-a7289e66d0a9:gemma-2-2b:gemmascope-transcoder-16k
    Top frequency features for prompt

    No Comments

    Negative Logits
     myſelf
    -0.91
    PerformLayout
    -0.80
     themſelves
    -0.79
     pleaſure
    -0.77
    ImageContext
    -0.77
     ſeveral
    -0.76
     leaſt
    -0.76
     reaſon
    -0.75
     Theſe
    -0.74
     iſt
    -0.74
    POSITIVE LOGITS
    GroupLayout
    0.49
    derry
    0.46
    makeText
    0.45
    dataclass
    0.44
    gitto
    0.43
    rrggbb
    0.42
    ,
    0.41
    CodeAttribute
    0.40
    IsString
    0.39
    Enders
    0.39
    Activations Density 0.708%

    No Known Activations