© 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. 7864
    Prev
    Next
    INDEX
    Explanations

    words often used when writing math or other similar symbolic notation.

    oai_token-act-pair · gemini-2.0-flash

    Math and Sports

    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
    InputBorder
    -0.78
    AndEndTag
    -0.77
     nakalista
    -0.73
    RenderAtEndOf
    -0.64
    lujah
    -0.63
    Cyfeiriadau
    -0.62
    aarrggbb
    -0.62
    SharedCtor
    -0.60
     שוליים
    -0.59
    IVEREF
    -0.58
    POSITIVE LOGITS
     ExecuteAsync
    0.54
    buzo
    0.50
    Packets
    0.50
    Muz
    0.49
    Mu
    0.46
    läufe
    0.44
     National
    0.43
    ఔ
    0.43
    isContained
    0.43
     mu
    0.42
    Activations Density 1.845%

    No Known Activations