© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115177
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
    的新
    0.48
     nouvelles
    0.45
     moet
    0.42
    ਿਹ
    0.41
    लो
    0.39
    δι
    0.39
     diccionario
    0.39
     канди
    0.38
    岨
    0.38
    ிருக்கிறது
    0.38
    POSITIVE LOGITS
     Stroke
    0.36
    math
    0.36
     Unix
    0.35
     Aloha
    0.35
    event
    0.35
     Cup
    0.34
     onset
    0.34
     Championship
    0.34
     Criminal
    0.34
     Division
    0.33
    Activations Density 0.000%

    No Known Activations