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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1571
    Prev
    Next
    INDEX
    Explanations

    first initials followed by last names, optionally with middle initials

    oai_token-act-pair · gemini-2.0-flash

    say "period"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    <bos>
    -0.65
    ніципалі
    -0.56
    aarrggbb
    -0.55
     réguli
    -0.51
     Мексичка
    -0.51
     refusé
    -0.51
     répondu
    -0.51
     eléctricas
    -0.50
     cumplido
    -0.50
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
    Tembelea
    0.66
     }}$
    0.63
    ugu
    0.63
    +}\
    0.61
    }^{-}$
    0.60
     ""}
    0.60
    }^{-}\
    0.59
    +}$
    0.59
    ;$
    0.59
    }^{+}$
    0.58
    Activations Density 9.052%

    No Known Activations