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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12691
    Prev
    Next
    INDEX
    Explanations

    text related to titles, names, or processes

    oai_token-act-pair · gemini-2.0-flash

    Research reports/documentation

    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
    sproz
    -0.42
     follow
    -0.42
    jaardag
    -0.42
    beelding
    -0.41
    wnątrz
    -0.41
    ysł
    -0.40
     kaart
    -0.40
    </strong>
    -0.39
    LETED
    -0.38
     entendre
    -0.38
    POSITIVE LOGITS
    <bos>
    0.86
     فريبيس
    0.75
    WebElementEntity
    0.73
    providedIn
    0.70
    RenderAtEndOf
    0.69
    basicConfig
    0.68
     Мексичка
    0.67
    новништво
    0.66
    انجليز
    0.66
    Portail
    0.66
    Activations Density 1.953%

    No Known Activations