© 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. 148284
    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
    ER
    0.58
    ELL
    0.57
    1
    0.56
    via
    0.54
    i
    0.53
    utility
    0.52
    in
    0.51
    EA
    0.49
    ua
    0.48
    L
    0.48
    POSITIVE LOGITS
    ㎏
    0.51
    ोज़
    0.51
     jeśli
    0.50
     kinetic
    0.48
     wszel
    0.48
     keyboards
    0.45
     нейтро
    0.45
     dopiero
    0.44
     NSUInteger
    0.44
    벵
    0.43
    Activations Density 0.000%

    No Known Activations