© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62540
    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_11_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
    オ
    0.68
    会
    0.63
    能
    0.59
     is
    0.55
    エ
    0.55
    고
    0.54
    为
    0.54
    好
    0.53
    对
    0.52
    ال
    0.52
    POSITIVE LOGITS
    )».
    0.54
     強
    0.53
     veliko
    0.52
     考え
    0.52
    ÜR
    0.52
     จับ
    0.52
     artr
    0.49
     ल
    0.49
     条
    0.48
    ObjectUnderTest
    0.48
    Activations Density 0.000%

    No Known Activations