© 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. 127688
    Prev
    Next
    INDEX
    Explanations

    Eurocentric narratives

    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
     \"%
    0.45
    StartZ
    0.43
     ALLOYS
    0.39
    琍
    0.39
    يزات
    0.38
     Property
    0.38
     金属
    0.38
     $("
    0.38
     "%
    0.37
    ृत्व
    0.36
    POSITIVE LOGITS
    Greek
    0.70
     Greek
    0.66
     Greeks
    0.60
    Greece
    0.57
     greek
    0.54
    greek
    0.48
     griech
    0.45
     greco
    0.43
     grec
    0.43
     griego
    0.42
    Activations Density 0.062%

    No Known Activations