© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76849
    Prev
    Next
    INDEX
    Explanations

    say "v" 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_53_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
    wała
    0.40
     Wadd
    0.40
     WordPerfect
    0.39
    хода
    0.37
     Wilbur
    0.37
    uali
    0.36
     Writ
    0.36
    𒂵
    0.36
    ദന
    0.35
     Waz
    0.35
    POSITIVE LOGITS
     vi
    1.43
     VI
    1.41
     vie
    1.41
    VI
    1.40
    ヴィ
    1.34
    vi
    1.30
     Vie
    1.29
    Vie
    1.29
     Vi
    1.27
    Vi
    1.25
    Activations Density 0.007%

    No Known Activations