© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13080
    Prev
    Next
    INDEX
    Explanations

    text indicating a comparison or causal relationship

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.89
    CodedInputStream
    -0.56
    الحياه
    -0.55
    classifiers
    -0.54
    日閲覧
    -0.47
    idän
    -0.46
    XtraGrid
    -0.46
    fastjson
    -0.44
     flyknit
    -0.44
    ệc
    -0.44
    POSITIVE LOGITS
    :✨
    0.82
    aarrggbb
    0.73
    AndEndTag
    0.70
     arşivlendi
    0.63
     estimés
    0.62
    IntoConstraints
    0.62
    WEBPACK
    0.61
    oredCriteria
    0.61
    发表于
    0.61
    OGND
    0.60
    Activations Density 6.444%

    No Known Activations