© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161225
    Prev
    Next
    INDEX
    Explanations

    Certain/some followed by categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     ഭാഗ
    0.33
    ینس
    0.31
    เร็ว
    0.31
    ത്തിയാ
    0.31
    RefIn
    0.31
    Conflict
    0.31
     areas
    0.30
    매
    0.30
    𐰆
    0.30
    把我
    0.30
    POSITIVE LOGITS
     Zweifel
    0.35
     связь
    0.34
    एसआई
    0.32
     कुर्ता
    0.32
     chrysanthemum
    0.31
     seide
    0.31
     দিল্লির
    0.31
     பொ
    0.30
     ضر
    0.30
     Frequency
    0.30
    Activations Density 0.008%

    No Known Activations