© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36140
    Prev
    Next
    INDEX
    Explanations

    word count

    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_7_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
     আপনার
    0.32
     autres
    0.30
     ﺍﻟ
    0.30
    妳
    0.29
     andere
    0.29
     ﺍ
    0.29
    كثر
    0.29
    /
    0.28
     আপনি
    0.28
    あなたの
    0.28
    POSITIVE LOGITS
     demikian
    0.25
    и
    0.24
    ства
    0.23
    cknowled
    0.23
    但在
    0.22
     하지만
    0.22
     screenplay
    0.22
    asi
    0.22
    砭
    0.21
    тов
    0.21
    Activations Density 0.010%

    No Known Activations