© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10732
    Prev
    Next
    INDEX
    Explanations

    code files, file paths, and code syntax.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · 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
    WireFormatLite
    -0.76
    ագրություններ
    -0.73
    出版年
    -0.68
    InjectAttribute
    -0.67
     invokingState
    -0.64
    mybatisplus
    -0.63
    RotationOrder
    -0.63
    ArrowToggle
    -0.63
     resourceCulture
    -0.62
    WebElementEntity
    -0.62
    POSITIVE LOGITS
     
    0.32
     produce
    0.31
    Geografie
    0.31
     ſtate
    0.30
     produisons
    0.30
    وافق
    0.29
     producir
    0.29
    $
    0.28
     quæ
    0.28
    so
    0.28
    Activations Density 1.547%

    No Known Activations