© 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. 113439
    Prev
    Next
    INDEX
    Explanations

    unchanged/changed

    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
    ور
    1.52
    ם
    1.38
    ס
    1.29
    ้
    1.27
    를
    1.23
    ג
    1.21
     astron
    1.17
    k
    1.16
    אר
    1.14
    การ
    1.13
    POSITIVE LOGITS
    <0xAB>
    1.09
    ма
    1.09
    _
    1.09
    <0xA3>
    1.09
    <0xBB>
    1.09
    were
    1.08
    нить
    1.04
    <0xBE>
    1.03
    る
    1.02
    ۳
    1.01
    Activations Density 0.000%

    No Known Activations