© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11323
    Prev
    Next
    INDEX
    Explanations

    words related to government, law, and business schemes.

    oai_token-act-pair · gemini-2.0-flash

    scheme

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    
    -0.98
    =$("#
    -0.67
    AndEndTag
    -0.66
    الحياه
    -0.66
    DMETHOD
    -0.66
    CloseOperation
    -0.64
     تضيفلها
    -0.64
     clearColor
    -0.63
    riceps
    -0.63
    RectangleBorder
    -0.61
    POSITIVE LOGITS
    exitRule
    0.54
     resourceCulture
    0.42
     initComponents
    0.42
     comerciais
    0.42
    .
    0.40
    kezi
    0.36
    :+:
    0.36
    lerinde
    0.34
     Nacionales
    0.34
     we
    0.34
    Activations Density 11.934%

    No Known Activations