© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34931
    Prev
    Next
    INDEX
    Explanations

    sexist, feminist, misogynistic ideology

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    iin
    0.65
    લ્પ
    0.56
    ლება
    0.54
    បែប
    0.51
    iul
    0.51
    uil
    0.50
    yap
    0.50
    ምና
    0.50
    aing
    0.48
    腖
    0.47
    POSITIVE LOGITS
     sexist
    0.60
     Without
    0.56
     DC
    0.54
     GQ
    0.54
     sämt
    0.53
     misog
    0.52
     AC
    0.51
     кожа
    0.51
     Welche
    0.50
     Kotor
    0.50
    Activations Density 0.134%

    No Known Activations