© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156347
    Prev
    Next
    INDEX
    Explanations

    gerontocracy/ocracy

    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_2_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
    ר
    1.30
    -
    1.23
    া
    1.21
    لنا
    1.19
    يد
    1.17
    н
    1.17
    ார்
    1.13
     сдела
    1.13
     писа
    1.12
    ように
    1.09
    POSITIVE LOGITS
    m
    1.82
    d
    1.55
    c
    1.49
    it
    1.48
    )
    1.42
    un
    1.31
    ab
    1.30
    the
    1.29
    os
    1.27
    ren
    1.24
    Activations Density 0.001%

    No Known Activations