© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14329
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people based on country

    oai_token-act-pair · gemini-2.0-flash

    Nationalities and cultures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vietnamese
    -0.99
     India
    -0.96
     Pakistan
    -0.92
    India
    -0.91
     Ethiopia
    -0.89
     Vietnam
    -0.88
     Bangladesh
    -0.88
     Haitian
    -0.88
     Ethiopian
    -0.87
     INDIA
    -0.86
    POSITIVE LOGITS
     Audiodateien
    0.63
     فريبيس
    0.62
     AspNetCore
    0.55
    Hentet
    0.55
    queryInterface
    0.54
    UnknownFields
    0.52
     OFDb
    0.52
    <tfoot>
    0.52
    iola
    0.51
    Спасылкі
    0.50
    Activations Density 2.227%

    No Known Activations