© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11142
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific language, including symbols, equations, and descriptions of statistical analyses

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     offent
    -0.43
    findOrFail
    -0.42
     вперед
    -0.42
     public
    -0.40
     tå
    -0.39
     urusan
    -0.39
    inser
    -0.37
     function
    -0.36
     pokok
    -0.36
     —
    -0.35
    POSITIVE LOGITS
    enumi
    0.76
    帖最后由
    0.76
    ImageContext
    0.75
     Signalez
    0.75
    Personendaten
    0.75
    OGND
    0.73
     Вікіпе
    0.72
    MigrationBuilder
    0.71
     Infórmanos
    0.70
     dAtA
    0.69
    Activations Density 4.886%

    No Known Activations