© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109377
    Prev
    Next
    INDEX
    Explanations

    Italiano

    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_1_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
     for
    2.09
     is
    1.45
     and
    1.29
     of
    1.26
    j
    1.23
    ה
    1.23
     in
    1.16
    d
    1.13
     on
    1.12
     not
    1.09
    POSITIVE LOGITS
    únior
    1.22
    сон
    1.16
    она
    1.14
    ESIS
    1.11
    ンの
    1.10
    скім
    1.07
    يو
    1.06
    вард
    1.03
    می
    1.02
    каде
    1.00
    Activations Density 0.000%

    No Known Activations