© 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. 8893
    Prev
    Next
    INDEX
    Explanations

    mentions of specific countries and their leaders

    oai_token-act-pair · gemini-2.0-flash

    foreign language or transliterated terms

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

    Israel

    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
    BoxShadow
    -0.49
     RELEASE
    -0.45
     release
    -0.45
    atrices
    -0.44
     useContext
    -0.44
     Art
    -0.43
    Demografia
    -0.43
    륙
    -0.42
     compagni
    -0.42
     livrer
    -0.42
    POSITIVE LOGITS
     nakalista
    0.77
     esternos
    0.73
     Chwiliwch
    0.70
    EndGlobalSection
    0.69
     estekak
    0.66
     للاسماء
    0.66
     myſelf
    0.66
     Wikimedijinoj
    0.66
     transférez
    0.65
    GEBURTSDATUM
    0.64
    Activations Density 24.897%

    No Known Activations