© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84754
    Prev
    Next
    INDEX
    Explanations

    patatas

    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_0_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
    '
    2.05
    س
    1.66
     (
    1.65
     is
    1.64
    с
    1.41
    га
    1.37
    ס
    1.32
    ية
    1.26
    is
    1.24
     can
    1.23
    POSITIVE LOGITS
    ل
    1.25
    in
    1.22
    国内
    1.21
    一
    1.20
     راستہ
    1.19
    তীশ
    1.17
     तभी
    1.16
     جیتنے
    1.16
    inę
    1.14
    t
    1.14
    Activations Density 0.001%

    No Known Activations