© 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. 11402
    Prev
    Next
    INDEX
    Explanations

    sentences, or clauses within sentences, that are making claims or assertions of fact, especially when related to business and products.

    oai_token-act-pair · gemini-2.0-flash

    non-English characters and code-related tokens

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

    Research articles

    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
    migrationBuilder
    -0.85
    //
    -0.59
    uesia
    -0.53
    jme
    -0.52
    nonatomic
    -0.50
    protoc
    -0.48
     nonatomic
    -0.48
     חיצוניים
    -0.47
    endpush
    -0.46
    gapan
    -0.45
    POSITIVE LOGITS
    
    0.75
     الاطلاع
    0.69
    enumii
    0.69
     rhestr
    0.57
     initComponents
    0.57
    PullParser
    0.57
     Troop
    0.55
     Entered
    0.53
     _$
    0.53
     AttributeSet
    0.52
    Activations Density 1.298%

    No Known Activations