© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5683
    Prev
    Next
    INDEX
    Explanations

    HTML font style formatting

    oai_token-act-pair · gemini-2.0-flash

    style attributes in programming

    np_token-act-pair-logits · gpt-4o-mini

    font

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    脚注の使い方
    -0.61
    parsedMessage
    -0.59
    CppMethod
    -0.57
    tvguidetime
    -0.57
    IBarButtonItem
    -0.55
     createState
    -0.54
     MenuView
    -0.53
     Chasse
    -0.52
    <tfoot>
    -0.52
    ]]);
    -0.52
    POSITIVE LOGITS
    PointerException
    0.56
    FlatAppearance
    0.50
     size
    0.50
    size
    0.50
    GIVEREF
    0.49
     faced
    0.47
    URLException
    0.46
    มิ
    0.44
     apertura
    0.44
    weig
    0.43
    Activations Density 0.431%

    No Known Activations