© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212122
    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_20_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
    گ
    0.55
     Viol
    0.52
    و
    0.51
    स
    0.50
    В
    0.50
    М
    0.48
    ب
    0.48
    活动
    0.47
    Л
    0.46
    г
    0.46
    POSITIVE LOGITS
     denote
    0.49
     комитета
    0.48
     környez
    0.48
     normalize
    0.46
     точку
    0.46
     signify
    0.46
    ชัน
    0.45
     downlink
    0.45
     comité
    0.44
     persist
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.