© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33420
    Prev
    Next
    INDEX
    Explanations

    women's empowerment and history

    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_3_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
    ת
    0.83
    ח
    0.65
    م
    0.64
     камень
    0.64
    न
    0.61
    ব
    0.61
    ب
    0.60
    𝓃
    0.60
     alternativas
    0.59
     abril
    0.59
    POSITIVE LOGITS
    a
    0.84
    া
    0.81
    ه
    0.75
    _
    0.73
    。
    0.72
    在
    0.70
    。(
    0.68
    ați
    0.68
     in
    0.66
    ),
    0.65
    Activations Density 0.001%

    No Known Activations