© 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. 106806
    Prev
    Next
    INDEX
    Explanations

    VGA cable

    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
    ו
    1.70
    ா
    1.30
    тер
    1.24
    すでに
    1.22
    ார்க
    1.21
    و
    1.21
    م
    1.21
    रण
    1.19
    는
    1.18
    وک
    1.16
    POSITIVE LOGITS
     for
    2.27
    0
    1.49
     at
    1.45
    s
    1.29
     Improves
    1.20
     with
    1.19
     as
    1.19
    ED
    1.19
    /
    1.15
    ent
    1.14
    Activations Density 0.000%

    No Known Activations