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. 1738
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for equations and formulas

    oai_token-act-pair · gemini-2.0-flash

    aligned

    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
     Efq
    -0.79
     AssemblyCulture
    -0.76
     myſelf
    -0.73
    asantry
    -0.70
    EndGlobalSection
    -0.70
    Enllaces
    -0.69
    aughey
    -0.67
     bershka
    -0.66
    NUMX
    -0.66
    AsUp
    -0.65
    POSITIVE LOGITS
    }}}}
    0.56
    *}
    0.56
    TemporalType
    0.56
    :}
    0.54
    }:$
    0.53
    })^
    0.53
    }|
    0.50
    },\
    0.49
    }}}\
    0.49
    })+
    0.49
    Activations Density 5.512%

    No Known Activations