© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 200028
    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_27_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
     диагности
    0.45
    шему
    0.41
     inhom
    0.40
     ऑपरेट
    0.39
     overpriced
    0.39
    ⺠
    0.39
    鳖
    0.39
    ሳ
    0.38
    ♎
    0.38
     достав
    0.38
    POSITIVE LOGITS
     duly
    0.38
     Swedish
    0.38
    and
    0.37
    together
    0.37
    などを
    0.36
    ii
    0.36
    with
    0.36
     cham
    0.35
    after
    0.35
    edit
    0.34
    Activations Density 0.000%

    No Known Activations