© 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. 194645
    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
     Nac
    0.43
    лья
    0.40
     뜨
    0.39
    enciar
    0.39
     Yara
    0.39
     Barra
    0.38
     Bayer
    0.38
     ودي
    0.37
     Epp
    0.37
    祎
    0.36
    POSITIVE LOGITS
    ningen
    0.56
    ning
    0.54
    ningar
    0.53
    ninja
    0.52
    ningarna
    0.51
     ninja
    0.48
    nings
    0.46
    NING
    0.46
    Ninja
    0.45
    nin
    0.43
    Activations Density 0.000%

    No Known Activations