© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11674
    Prev
    Next
    INDEX
    Explanations

    the word "statement" preceded by a verb of speaking

    oai_token-act-pair · gemini-2.0-flash

    statement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WebElementEntity
    -0.85
    GEBURTS
    -0.84
    Espèce
    -0.82
    __':
    -0.76
     autorytatywna
    -0.75
    PostInfinity
    -0.72
    enterOuterAlt
    -0.71
     bezeichneter
    -0.71
    ImageContext
    -0.70
    ++]=
    -0.70
    POSITIVE LOGITS
    tioned
    0.34
    NonNull
    0.33
    HttpFoundation
    0.31
    通販
    0.31
     days
    0.31
    asjonen
    0.30
     dager
    0.30
    étranger
    0.30
     chaining
    0.29
    uksen
    0.28
    Activations Density 0.157%

    No Known Activations