© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226616
    Prev
    Next
    INDEX
    Explanations

    van followed by a surname

    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_6_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
    at
    1.56
    s
    1.43
    ed
    1.40
    ف
    1.30
    in
    1.26
    א
    1.24
    am
    1.23
    o
    1.16
    em
    1.15
    e
    1.13
    POSITIVE LOGITS
    ᱼ
    0.85
    ုံး
    0.84
     ngừa
    0.84
    ScreenWidth
    0.83
     gstlal
    0.82
    ựng
    0.81
     школы
    0.80
    она
    0.80
    нер
    0.80
     υψη
    0.80
    Activations Density 0.000%

    No Known Activations