© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 921
    Prev
    Next
    INDEX
    Explanations

    code snippets from many coding languages, including some file paths.

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
     AssemblyCulture
    -0.82
    SharedDtor
    -0.77
    bootstrapcdn
    -0.75
    errHandler
    -0.74
    ьаж
    -0.73
    )");
    -0.73
    windowFixed
    -0.71
    XmlAccessType
    -0.69
     Hift
    -0.69
    ніципалі
    -0.68
    POSITIVE LOGITS
     gql
    0.48
     Ah
    0.47
     C
    0.46
     adopt
    0.45
     trade
    0.44
     nim
    0.42
     N
    0.42
     ah
    0.41
     m
    0.41
    openzeppelin
    0.40
    Activations Density 1.190%

    No Known Activations