© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16073
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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_40_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
     ARR
    0.42
    ilitar
    0.39
     Nauchno
    0.39
     Capacity
    0.38
    Capacity
    0.37
     Absorption
    0.37
     ഉത്തര
    0.35
     Леони
    0.35
    ('-');
    0.35
     confirms
    0.35
    POSITIVE LOGITS
     twelfth
    0.49
    ×
    0.48
     twelve
    0.45
    有効
    0.39
    dzie
    0.38
    цтва
    0.38
     thirteenth
    0.38
     maal
    0.38
    nez
    0.38
     eleventh
    0.38
    Activations Density 0.020%

    No Known Activations