© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19052
    Prev
    Next
    INDEX
    Explanations

    gender disproportion in Asia

    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_34_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
     serr
    0.38
    òng
    0.36
    WS
    0.36
    paw
    0.35
     extrem
    0.35
     extremo
    0.35
    احت
    0.34
     altına
    0.34
    <!---
    0.34
     പാര്‍
    0.34
    POSITIVE LOGITS
    基準
    0.41
    แก้ไข
    0.41
    desktop
    0.39
    зова
    0.38
     ENT
    0.38
    ствуйте
    0.38
     Sad
    0.37
     যতই
    0.37
     ориенти
    0.37
     saturated
    0.36
    Activations Density 0.002%

    No Known Activations