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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1989
    Prev
    Next
    INDEX
    Explanations

    articles plus adjectives, location of UK, and references to medical facilities

    oai_token-act-pair · gemini-2.0-flash

    terms related to governments and organizations

    np_token-act-pair-logits · gpt-4o-mini

    countries/organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     bénévoles
    -0.77
     prêtres
    -0.73
     touristes
    -0.73
     débats
    -0.72
     prisonniers
    -0.72
     négociations
    -0.72
     EconPapers
    -0.71
     vœux
    -0.70
    Cyfeiriadau
    -0.69
    
    -0.68
    POSITIVE LOGITS
     governments
    1.44
     Governments
    1.35
     worlds
    1.34
     nations
    1.30
     countries
    1.30
     companies
    1.17
     societies
    1.16
     publics
    1.16
     compan
    1.13
     firms
    1.13
    Activations Density 1.890%

    No Known Activations