© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8975
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by the word "said."

    oai_token-act-pair · gemini-2.0-flash

    say "said"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    liothèque
    -0.73
    ftagPool
    -0.73
    styleType
    -0.71
    multer
    -0.70
     ModelExpression
    -0.68
    bnf
    -0.67
     typelib
    -0.66
    complexContent
    -0.65
     intStringLen
    -0.64
     @"/
    -0.64
    POSITIVE LOGITS
     يتيمه
    0.53
    holdet
    0.49
    ADVERTISEMENT
    0.41
     celebrates
    0.40
     poffe
    0.40
    stø
    0.39
    estimates
    0.39
    seems
    0.39
     celebrate
    0.39
     tristes
    0.39
    Activations Density 6.089%

    No Known Activations