© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 180101
    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_50_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
     Aff
    0.48
     জানা
    0.42
     Cape
    0.41
    Affine
    0.41
    딧
    0.40
     Surveillance
    0.40
    eward
    0.39
    Aff
    0.39
    Cape
    0.39
     Вай
    0.39
    POSITIVE LOGITS
     قوم
    0.71
     قومی
    0.70
     الق
    0.65
    قوم
    0.63
    وم
    0.56
     Q
    0.55
     সম্প্র
    0.55
    national
    0.53
    Nation
    0.50
     nationally
    0.49
    Activations Density 0.000%

    No Known Activations