© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40718
    Prev
    Next
    INDEX
    Explanations

    never + verb

    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_3_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
    a
    1.64
    in
    1.32
    an
    1.23
    as
    1.18
    i
    1.13
    art
    1.11
    er
    1.03
    at
    1.01
    ier
    1.01
    af
    0.96
    POSITIVE LOGITS
    ের
    1.20
    ן
    1.18
    ς
    1.13
    ם
    1.11
     on
    1.02
    )$,
    0.96
    ों
    0.96
    ۰
    0.91
    ओं
    0.89
    ים
    0.89
    Activations Density 0.003%

    No Known Activations