© 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. 203959
    Prev
    Next
    INDEX
    Explanations

    say ")"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    '।
    0.39
    illeri
    0.39
    üglich
    0.38
     '',
    0.38
     ፣
    0.37
    ‌,
    0.37
    nals
    0.36
     başlayalım
    0.35
    ’।
    0.34
     outp
    0.34
    POSITIVE LOGITS
    ढ़ी
    0.37
    লেন
    0.34
    ثیر
    0.32
    رويج
    0.32
     coerce
    0.32
    ⇓
    0.32
     worden
    0.31
     ক্ষুধ
    0.31
     maha
    0.31
    编辑器
    0.31
    Activations Density 0.024%

    No Known Activations