© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81183
    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_31_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
    DetailsService
    0.29
    Commod
    0.29
    твор
    0.28
     Kaleidoscope
    0.28
    倸
    0.27
     пово
    0.27
     ناس
    0.27
    アリング
    0.27
    
    0.27
     commodity
    0.26
    POSITIVE LOGITS
     विष्णु
    0.30
    extré
    0.28
    ostí
    0.27
    数は
    0.27
    alex
    0.26
    rai
    0.25
    ੂੰ
    0.25
    সময়
    0.25
     posiada
    0.25
     수는
    0.25
    Activations Density 0.000%

    No Known Activations