© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40510
    Prev
    Next
    INDEX
    Explanations

    baking

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     cet
    0.49
     S
    0.42
     compass
    0.41
     re
    0.40
     adolescent
    0.39
     gar
    0.38
     quad
    0.38
     c
    0.38
     saff
    0.36
     rych
    0.35
    POSITIVE LOGITS
    㴡
    0.40
    ژگی
    0.38
    верса
    0.37
    пня
    0.37
    ILLA
    0.37
    AUTH
    0.36
    CHAIN
    0.36
     সিংহের
    0.36
    酩
    0.36
    諺
    0.36
    Activations Density 0.001%

    No Known Activations