© 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. 9083
    Prev
    Next
    INDEX
    Explanations

    terms associated with race

    oai_token-act-pair · gemini-2.0-flash

    terms related to race and ethnicity

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

    black

    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
     pouvoirs
    -0.49
     verdadeira
    -0.47
     totiž
    -0.45
     écrans
    -0.45
     legale
    -0.43
     devons
    -0.42
    obacz
    -0.42
    ']->
    -0.42
     vœux
    -0.42
    jspx
    -0.41
    POSITIVE LOGITS
    OGND
    0.75
     SIMBAD
    0.73
    MigrationBuilder
    0.71
     improvisation
    0.69
    CloseOperation
    0.68
     esternos
    0.66
    RenderAtEndOf
    0.64
     adulthood
    0.63
    WebVitals
    0.62
     Italijani
    0.62
    Activations Density 2.110%

    No Known Activations