© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112212
    Prev
    Next
    INDEX
    Explanations

    tangy or Tanzanian

    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
    Not in Any Lists

    No Comments

    Negative Logits
    在
    1.52
    is
    1.41
     in
    1.33
    h
    1.28
    é
    1.23
    도
    1.17
    '
    1.15
    as
    1.13
    os
    1.13
     as
    1.13
    POSITIVE LOGITS
     that
    1.23
    יות
    1.18
    ни
    1.16
     sortir
    1.16
    ﺍ
    1.15
     que
    1.14
    تها
    1.12
    ים
    1.11
    that
    1.07
    ্টার
    1.05
    Activations Density 0.002%

    No Known Activations