© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242143
    Prev
    Next
    INDEX
    Explanations

    foreign language characters or words

    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_25_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
     partisan
    0.33
     Rifle
    0.30
     Series
    0.30
     Springer
    0.29
     relentless
    0.29
     both
    0.29
     dreamy
    0.29
    2
    0.29
     $
    0.28
     entire
    0.28
    POSITIVE LOGITS
     ovipares
    0.38
     pabb
    0.33
    իտ
    0.33
     jiné
    0.33
    
    0.32
     istit
    0.32
     úlo
    0.32
    Karnataka
    0.32
     těž
    0.32
     práv
    0.31
    Activations Density 0.000%

    No Known Activations