© 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. 30526
    Prev
    Next
    INDEX
    Explanations

    administer

    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
    ری
    0.57
    ﻮ
    0.51
     bullies
    0.48
     fous
    0.47
    ն
    0.47
    纡
    0.46
     fclose
    0.46
     baños
    0.46
     dimensiones
    0.44
     reduz
    0.44
    POSITIVE LOGITS
    and
    0.49
    '
    0.49
    oral
    0.45
    were
    0.45
    ended
    0.44
    ISBN
    0.44
    ে
    0.44
    that
    0.43
    plus
    0.43
    ed
    0.42
    Activations Density 0.003%

    No Known Activations