© 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. 113422
    Prev
    Next
    INDEX
    Explanations

    chef or cook

    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
     in
    1.23
    il
    1.13
    -
    1.11
    ב
    1.09
    .
    1.04
    +
    1.04
    드
    1.04
    ok
    0.97
    ने
    0.97
    ut
    0.93
    POSITIVE LOGITS
    t
    1.23
    いた
    1.17
    étale
    1.16
     други
    1.16
     ieder
    1.15
    ਾ
    1.15
    ான்
    1.13
     étend
    1.13
     desempeñ
    1.13
    ル
    1.12
    Activations Density 0.001%

    No Known Activations