© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205428
    Prev
    Next
    INDEX
    Explanations

    ne...pas negation

    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_10_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
    0.66
     are
    0.63
     anima
    0.63
     on
    0.62
     contenders
    0.61
     }
    0.61
     import
    0.61
     indice
    0.61
     elke
    0.60
     amp
    0.60
    POSITIVE LOGITS
    as
    0.78
    də
    0.72
    ет
    0.71
    ﻊ
    0.70
    ದುಕೊಳ್ಳ
    0.68
    getAsDouble
    0.67
    ен
    0.67
    ৪৭
    0.67
    does
    0.66
    cannot
    0.66
    Activations Density 0.004%

    No Known Activations