© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6350
    Prev
    Next
    INDEX
    Explanations

    various segments of code, notation, and/or unusual terms

    oai_token-act-pair · gemini-2.0-flash

    Code/math/legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    PreferredItem
    -0.63
    aspectj
    -0.59
    aarrggbb
    -0.57
     виправивши
    -0.57
    >{@
    -0.54
    GEBURTSDATUM
    -0.53
     ModelExpression
    -0.52
     Wikimedijinoj
    -0.52
    ंदीखरीदारी
    -0.51
    évaluateur
    -0.51
    POSITIVE LOGITS
    gon
    0.69
    gab
    0.65
     Theſe
    0.59
    gard
    0.59
    gid
    0.57
    gav
    0.57
    gated
    0.56
     Reſ
    0.56
    gö
    0.56
    g
    0.56
    Activations Density 0.618%

    No Known Activations