© 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. 134083
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     bauen
    0.42
    bygg
    0.42
     rosy
    0.41
     ちゃう
    0.39
     Grun
    0.39
    dpy
    0.39
    nia
    0.38
    ọ
    0.38
    Cm
    0.37
    不由
    0.37
    POSITIVE LOGITS
    パッド
    0.38
    履歴
    0.37
    lland
    0.37
     extremes
    0.36
    extreme
    0.36
     numer
    0.36
    لط
    0.36
     exponents
    0.35
    لمات
    0.35
    ම්භ
    0.35
    Activations Density 0.000%

    No Known Activations