Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5822
    Prev
    Next
    INDEX
    Explanations

    clauses after the word "but" or words indicating exception, contradiction, or qualification.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

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

    But/And

    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
    andaag
    -0.51
    matchCondition
    -0.50
     of
    -0.43
    onStop
    -0.42
    still
    -0.41
    NavController
    -0.41
    sek
    -0.41
     still
    -0.40
    иболее
    -0.40
    DoubleQuotes
    -0.39
    POSITIVE LOGITS
    WithIOException
    0.77
    MigrationBuilder
    0.75
    
    0.73
     typelib
    0.71
    ThroughAttribute
    0.69
    évaluateur
    0.68
     ainfi
    0.67
    yntaxException
    0.65
     pleaſure
    0.63
     graça
    0.63
    Activations Density 1.693%

    No Known Activations