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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16262
    Prev
    Next
    INDEX
    Explanations

    passages discussing multiculturalism and demographic groups

    oai_token-act-pair · gemini-2.0-flash

    diversity and culture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    
    -0.62
    providedIn
    -0.60
    icoot
    -0.59
    cticut
    -0.55
    }])
    -0.54
    ❹
    -0.53
    inburgh
    -0.51
    tableFuture
    -0.50
    єра
    -0.49
    Diweddarwch
    -0.49
    POSITIVE LOGITS
     мәкал
    0.58
    Notae
    0.55
    хьтан
    0.55
     reflected
    0.54
    AllowUser
    0.52
     Letras
    0.51
     représentation
    0.50
    LookAnd
    0.50
     represented
    0.50
     représent
    0.49
    Activations Density 0.747%

    No Known Activations