© 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. 162676
    Prev
    Next
    INDEX
    Explanations

    names and French text parts

    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
    Negative Logits
     was
    1.37
     to
    1.31
     it
    1.22
     you
    1.15
    '
    1.13
    ',
    1.12
     isn
    1.12
    ?
    1.09
     plagiarism
    1.08
    h
    1.07
    POSITIVE LOGITS
    2
    0.96
    in
    0.92
    as
    0.89
    েলে
    0.89
    .
    0.88
    나
    0.88
    通
    0.88
    ান
    0.86
    𝗹
    0.85
    日閲覧
    0.84
    Activations Density 0.008%

    No Known Activations