© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13088
    Prev
    Next
    INDEX
    Explanations

    Android code

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     the
    -0.71
     bu
    -0.69
     qu
    -0.67
     tr
    -0.67
     di
    -0.66
     la
    -0.66
     var
    -0.66
     data
    -0.66
    bootstrapcdn
    -0.65
     da
    -0.63
    POSITIVE LOGITS
     itſelf
    1.11
     myſelf
    0.93
     faſt
    0.91
     ſever
    0.89
    ſelf
    0.89
     ſte
    0.88
     reaſon
    0.88
     unſ
    0.87
     raiſ
    0.87
    ſelves
    0.87
    Activations Density 1.659%

    No Known Activations