© 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. 193469
    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
     representa
    0.40
     реши
    0.38
    𝐜
    0.37
    plectic
    0.34
    ారణ
    0.34
     passionately
    0.34
    𝙩
    0.34
    𝘱
    0.34
    埓
    0.34
    летов
    0.34
    POSITIVE LOGITS
    桀
    0.37
    그러나
    0.35
     Mich
    0.35
     Lobkovic
    0.35
     કુ
    0.34
     Sied
    0.34
    owanym
    0.34
     különb
    0.33
     আজকাল
    0.33
    薗
    0.33
    Activations Density 0.000%

    No Known Activations