© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4741
    Prev
    Next
    INDEX
    Explanations

    information about baseball player statistics, trades, and teams

    oai_token-act-pair · gemini-2.0-flash

    trading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     mode
    -0.47
     rep
    -0.45
    rep
    -0.45
    ri
    -0.44
    re
    -0.43
     n
    -0.43
     разо
    -0.43
     re
    -0.43
    ,
    -0.43
     
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.98
     незавершена
    0.92
    DockStyle
    0.88
    principalColumn
    0.88
    ArgsConstructor
    0.88
     للمعارف
    0.85
     ujednoznacz
    0.83
    الحياه
    0.83
    rungsseite
    0.82
     nahilalakip
    0.77
    Activations Density 1.519%

    No Known Activations