© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226581
    Prev
    Next
    INDEX
    Explanations

    food handling activities

    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_6_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
     ancienne
    0.90
     Ε
    0.89
    ה
    0.89
    お
    0.89
     allemand
    0.87
    सभी
    0.82
    которы
    0.82
    ０
    0.81
    ש
    0.80
    Nicht
    0.80
    POSITIVE LOGITS
    at
    1.13
    ing
    1.11
    om
    1.04
    ิ
    1.00
    ed
    0.98
    ic
    0.94
    ے
    0.93
    age
    0.88
    ai
    0.88
    as
    0.87
    Activations Density 0.002%

    No Known Activations