© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192297
    Prev
    Next
    INDEX
    Explanations

    reputable

    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_4_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
    م
    1.08
    ب
    1.06
    د
    1.00
     robuste
    0.96
    ك
    0.94
    مكن
    0.92
    ح
    0.92
     kurze
    0.91
    دين
    0.90
    他对
    0.90
    POSITIVE LOGITS
    od
    1.59
    is
    1.47
    u
    1.27
    ک
    1.25
    v
    1.23
    ین
    1.20
    ifications
    1.09
    0
    1.09
     as
    1.08
    ılar
    1.06
    Activations Density 0.009%

    No Known Activations