© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13782
    Prev
    Next
    INDEX
    Explanations

    code-related terms like chipset, graphics, RAM, and canvas

    oai_token-act-pair · gemini-2.0-flash

    graphics code and rendering

    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
    بوابة
    -0.62
    Portail
    -0.53
    WEBPACK
    -0.52
     متعلقه
    -0.50
    ameter
    -0.49
    popd
    -0.48
    SPP
    -0.47
     Alcott
    -0.46
    verteilung
    -0.46
    pushFollow
    -0.45
    POSITIVE LOGITS
    ".
    0.67
    >");
    0.66
    )";
    0.64
     context
    0.61
     صوتيه
    0.60
     createContext
    0.60
    />";
    0.59
     graphics
    0.57
     contexte
    0.57
    "]);
    0.57
    Activations Density 1.533%

    No Known Activations