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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16300
    Prev
    Next
    INDEX
    Explanations

    sensory words combined with marks and injuries on the body or objects

    oai_token-act-pair · gemini-2.0-flash

    seemingly random tokens

    np_token-act-pair-logits · gemini-2.0-flash

    Damage and imperfections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.77
     estekak
    -0.66
     cair
    -0.59
    __*/
    -0.58
     moschino
    -0.57
     createContext
    -0.57
    ]")]
    -0.57
     ་་
    -0.55
    .');
    -0.54
    )"),
    -0.54
    POSITIVE LOGITS
    oredCriteria
    0.47
    bindingNavigator
    0.44
    mybatisplus
    0.44
     weer
    0.43
    ToFile
    0.43
     szint
    0.43
    VersionUID
    0.42
    ตัว
    0.42
    ناية
    0.42
    HideFlags
    0.42
    Activations Density 2.172%

    No Known Activations