© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1292
    Prev
    Next
    INDEX
    Explanations

    text within parentheses

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     <",
    -0.57
    <bos>
    -0.56
    irvana
    -0.54
    ruppen
    -0.53
    संद
    -0.48
     Мексичка
    -0.48
     Découvrez
    -0.47
    DrawerToggle
    -0.47
     Meksiku
    -0.47
    SerializedSize
    -0.46
    POSITIVE LOGITS
     kaynağından
    0.65
     /\.(
    0.58
    extAlignment
    0.58
    lables
    0.56
     MediatR
    0.55
     électroniques
    0.55
    invokeLater
    0.53
    󠁢
    0.53
    кнул
    0.52
    OrEmpty
    0.51
    Activations Density 1.884%

    No Known Activations