© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129715
    Prev
    Next
    INDEX
    Explanations

    Much

    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_50_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
     Kyng
    0.38
    閫
    0.38
     voorbeeld
    0.37
     පෙර
    0.37
     ശേഷം
    0.36
     connaissances
    0.36
    oxycholic
    0.35
     liik
    0.35
     거기
    0.35
     නො
    0.34
    POSITIVE LOGITS
    পাতা
    0.34
    '],
    0.34
    ))],
    0.33
    Ꭱ
    0.33
    bala
    0.32
    琳
    0.32
    MENT
    0.32
     Retention
    0.32
    ':
    0.31
     Margin
    0.31
    Activations Density 0.001%

    No Known Activations