© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145435
    Prev
    Next
    INDEX
    Explanations

    say "u" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     forfeited
    0.42
    irii
    0.41
    itorios
    0.39
    ტორი
    0.38
     danne
    0.38
    稦
    0.37
     chips
    0.37
     queryString
    0.37
     tratan
    0.36
    تد
    0.36
    POSITIVE LOGITS
    reach
    0.44
    r
    0.43
    rune
    0.43
    none
    0.39
    roy
    0.39
    クリ
    0.39
    lone
    0.38
    rint
    0.38
    mym
    0.38
    foot
    0.38
    Activations Density 0.000%

    No Known Activations