© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11892
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe physical action sometimes including violence.

    oai_token-act-pair · gemini-2.0-flash

    fast and forceful motion

    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
     Infórmanos
    -0.90
    eriks
    -0.68
    országban
    -0.66
    Obrázky
    -0.66
    География
    -0.62
    providedIn
    -0.60
     flew
    -0.60
    abestanden
    -0.58
    Portály
    -0.57
    addContainerGap
    -0.57
    POSITIVE LOGITS
    AnchorStyles
    0.55
    RectangleBorder
    0.46
    ?}",
    0.46
    Begriffsklä
    0.44
    }*/
    0.43
    mbar
    0.43
     ModelExpression
    0.41
    tagext
    0.40
    }*/
    0.39
    zug
    0.38
    Activations Density 10.091%

    No Known Activations