© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203755
    Prev
    Next
    INDEX
    Explanations

    pages

    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_56_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
     bite
    0.56
    bite
    0.43
     Bite
    0.41
     save
    0.39
    ebo
    0.39
    ંટ
    0.37
    ven
    0.36
    ϝ
    0.36
     Leib
    0.36
    咬
    0.35
    POSITIVE LOGITS
     page
    1.23
    page
    1.10
     pages
    1.04
     leaf
    0.99
     Page
    0.96
    Page
    0.93
     página
    0.93
     pagina
    0.92
     cue
    0.91
    ページ
    0.88
    Activations Density 0.000%

    No Known Activations