© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77472
    Prev
    Next
    INDEX
    Explanations

    summary docstrings

    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_29_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
     മതി
    0.36
     มี
    0.36
    มี
    0.35
     विद्व
    0.34
     అంతే
    0.34
    !
    0.34
    imed
    0.33
                        
    0.33
    amaz
    0.33
    有
    0.33
    POSITIVE LOGITS
     vials
    0.40
     heterozyg
    0.38
     horseradish
    0.37
     organelles
    0.37
    স্থান
    0.36
     chitin
    0.36
     আবদ্ধ
    0.36
    ચર
    0.35
    Jährige
    0.35
     weigh
    0.35
    Activations Density 0.005%

    No Known Activations