© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7862
    Prev
    Next
    INDEX
    Explanations

    the phrase "take part"

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     själva
    -0.60
    citep
    -0.53
    reuung
    -0.52
    pré
    -0.52
     afuera
    -0.52
    were
    -0.52
     něm
    -0.50
    ↵
    -0.50
     öne
    -0.48
    Were
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.88
    MergeFrom
    0.82
    webElementXpaths
    0.82
    )");
    0.82
    Искәрмәләр
    0.77
    OrBuilder
    0.76
    ArgsConstructor
    0.75
    )";
    0.74
    WithIOException
    0.74
     pinulongan
    0.73
    Activations Density 0.156%

    No Known Activations