© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15883
    Prev
    Next
    INDEX
    Explanations

    lines of code that import libraries or other packages

    oai_token-act-pair · gemini-2.0-flash

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    writeFieldEnd
    -0.63
     ModelExpression
    -0.57
    TagMode
    -0.55
    didSet
    -0.52
    enumerate
    -0.52
    adaptiveStyles
    -0.52
    bootstrapcdn
    -0.50
     ControllerBase
    -0.49
    {...
    -0.49
     مشين
    -0.49
    POSITIVE LOGITS
    <bos>
    0.70
     Dijo
    0.60
     quoique
    0.60
    İş
    0.56
    reactstrap
    0.56
    TintMode
    0.56
     Theſe
    0.56
     frontale
    0.55
    mybatisplus
    0.54
     Profitez
    0.54
    Activations Density 0.187%

    No Known Activations