© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101479
    Prev
    Next
    INDEX
    Explanations

    output

    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_44_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
    출
    0.52
    vý
    0.41
     출
    0.38
     бою
    0.38
     xuất
    0.37
    输出
    0.37
     త
    0.35
    utip
    0.35
     भीम
    0.35
    vykor
    0.35
    POSITIVE LOGITS
    鱈
    0.40
     loud
    0.37
     syn
    0.35
     cyan
    0.35
     con
    0.35
     Syn
    0.34
    landish
    0.34
    ď
    0.34
    Rob
    0.33
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.33
    Activations Density 0.007%

    No Known Activations