© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13066
    Prev
    Next
    INDEX
    Explanations

    mentions of "F1" or "Formula 1" alongside related words like "game" or "racing", and developer names like "Codemasters", "Electronic Arts", and "Psygnosis".

    oai_token-act-pair · gemini-2.0-flash

    Games and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    /*++
    -0.49
     aikana
    -0.40
    Cw
    -0.39
    ArrowToggle
    -0.39
     Carriers
    -0.38
    Bibliografia
    -0.38
     cár
    -0.37
     sounds
    -0.37
     Sounds
    -0.36
    пс
    -0.36
    POSITIVE LOGITS
    ftagPool
    0.91
    matchCondition
    0.89
     EconPapers
    0.87
    MLLoader
    0.75
    DoubleQuotes
    0.75
    adpleegd
    0.75
    出版年
    0.74
    mybatisplus
    0.73
    InjectAttribute
    0.73
    plotlib
    0.71
    Activations Density 0.558%

    No Known Activations