© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47065
    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_13_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
     Akan
    0.50
     akan
    0.50
    लाई
    0.49
     tatha
    0.49
     Hanya
    0.48
     podr
    0.47
     Hendrik
    0.46
     Tatha
    0.45
     bunu
    0.45
    라
    0.45
    POSITIVE LOGITS
    築
    0.47
     fragrance
    0.45
     parsing
    0.44
    myData
    0.44
     amnesty
    0.44
     bleaching
    0.44
    avance
    0.44
    פות
    0.44
    acles
    0.43
    กร
    0.43
    Activations Density 0.000%

    No Known Activations