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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12241
    Prev
    Next
    INDEX
    Explanations

    topics related to race, education, and media literacy

    oai_token-act-pair · gemini-2.0-flash

    society and culture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_23/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
    onoi
    -0.53
     Administrativna
    -0.51
     consultato
    -0.47
    AxisAlignment
    -0.46
    mius
    -0.44
    OLIC
    -0.41
     synthèse
    -0.41
     δε
    -0.40
     Bean
    -0.40
     sou
    -0.40
    POSITIVE LOGITS
     constructions
    0.80
     construction
    0.78
    ⓧ
    0.75
     فريبيس
    0.74
    construction
    0.73
    InputBorder
    0.73
    UrlResolution
    0.72
     Construction
    0.72
    RegressionTest
    0.71
     AspNetCore
    0.71
    Activations Density 3.520%

    No Known Activations