© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109298
    Prev
    Next
    INDEX
    Explanations

    auscultation

    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_1_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
    ation
    1.35
    و
    1.23
    8
    1.21
    ama
    1.16
    اً
    1.14
    的核心
    1.14
    ang
    1.08
    اذ
    1.04
    اين
    1.04
     ήταν
    1.03
    POSITIVE LOGITS
    i
    1.46
    ד
    1.11
    ри
    1.09
    ש
    1.08
    st
    1.00
    ล
    0.99
    い
    0.98
    y
    0.98
    な
    0.97
    v
    0.96
    Activations Density 0.000%

    No Known Activations