© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133700
    Prev
    Next
    INDEX
    Explanations

    religious intolerance

    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_1_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
    I
    1.24
    もら
    1.07
     to
    1.03
     یک
    1.00
    แต่
    1.00
    の内
    1.00
     are
    0.99
    ，
    0.98
     but
    0.96
    も
    0.95
    POSITIVE LOGITS
    ad
    1.28
    ون
    1.17
    us
    1.09
    ul
    1.05
    il
    1.04
    تالي
    1.04
    p
    1.01
    ت
    0.97
    茼
    0.97
    utico
    0.96
    Activations Density 0.002%

    No Known Activations