© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10990
    Prev
    Next
    INDEX
    Explanations

    source code and hardware parameters like cache size, block width, and associativity

    oai_token-act-pair · gemini-2.0-flash

    configuration/parameter settings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.93
     pinulongan
    -0.87
    tvguidetime
    -0.81
    تقاوى
    -0.76
    parsedMessage
    -0.71
    Diweddarwch
    -0.67
     unknownFields
    -0.66
    Jeografia
    -0.65
    amentals
    -0.65
    tôi
    -0.63
    POSITIVE LOGITS
    OOTDTY
    0.47
     saluran
    0.41
     الحره
    0.41
     Channel
    0.41
    ビア
    0.40
     Verhaltens
    0.39
    存于互联网档案馆
    0.38
    gatsby
    0.37
    ấp
    0.37
    Shell
    0.37
    Activations Density 1.026%

    No Known Activations