© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207070
    Prev
    Next
    INDEX
    Explanations

    American identifying professions or origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    א
    0.78
     you
    0.78
    ન
    0.77
    あなたの
    0.77
    یت
    0.73
    คุณ
    0.72
    ア
    0.72
    ब
    0.71
     your
    0.70
     immunology
    0.69
    POSITIVE LOGITS
    and
    0.81
    coefficients
    0.80
    vas
    0.77
    as
    0.74
    ven
    0.72
    로서
    0.71
    ark
    0.70
    il
    0.69
    vet
    0.67
     Coefficient
    0.67
    Activations Density 0.007%

    No Known Activations