© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200015
    Prev
    Next
    INDEX
    Explanations

    Anti-Defamation League

    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_37_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
    ഹ്
    0.41
     руководи
    0.39
    كي
    0.37
    شع
    0.37
    কর্ম
    0.35
    윙
    0.35
     Jews
    0.34
     स्ट्रा
    0.34
     vezető
    0.34
     Talmud
    0.34
    POSITIVE LOGITS
    ClrBit
    0.38
     disple
    0.37
     Yeti
    0.37
     dissatisfied
    0.36
    الل
    0.36
     unequal
    0.36
     美
    0.35
     Asante
    0.35
     Bokeh
    0.35
    ഷ്ട
    0.35
    Activations Density 0.001%

    No Known Activations