© 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. 162475
    Prev
    Next
    INDEX
    Explanations

    М или Д

    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
     to
    1.61
    大
    1.61
     for
    1.52
     or
    1.40
     as
    1.23
     are
    1.22
     was
    1.17
    ne
    1.16
     of
    1.16
     on
    1.12
    POSITIVE LOGITS
    Makanan
    1.17
    January
    1.13
    يها
    1.13
    し
    1.13
    ও
    1.13
    ﻱ
    1.12
    ков
    1.08
    Apakah
    1.03
    Hasil
    0.98
    ین
    0.97
    Activations Density 0.001%

    No Known Activations