© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143531
    Prev
    Next
    INDEX
    Explanations

    protected

    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_46_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
    segment
    0.46
     segment
    0.43
     section
    0.40
    ུང་
    0.39
     communism
    0.38
     блок
    0.37
    =".$
    0.37
     খাজ
    0.37
     unprotected
    0.36
     जगदीश
    0.36
    POSITIVE LOGITS
     ஒப்ப
    0.37
    Meta
    0.36
     rv
    0.36
    정보
    0.36
    rv
    0.36
    UpDown
    0.36
    情報
    0.35
     જાહેર
    0.35
    lymp
    0.35
    麃
    0.35
    Activations Density 0.001%

    No Known Activations