© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83793
    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_23_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
    oce
    0.42
    oida
    0.42
     earthen
    0.41
     capitaine
    0.40
    odend
    0.40
    ampionship
    0.39
     gyd
    0.38
    土
    0.38
     itth
    0.37
     yath
    0.37
    POSITIVE LOGITS
    推出
    0.44
    られる
    0.42
    应用
    0.42
     устройство
    0.42
     ứng
    0.41
    される
    0.40
    действие
    0.40
     иденти
    0.40
    鸦
    0.40
     устрой
    0.40
    Activations Density 0.000%

    No Known Activations