© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156336
    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_2_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
    них
    1.20
    리로
    1.13
    どうしても
    1.10
     marquées
    1.09
    unuz
    1.07
    ну
    1.04
    ви
    1.02
    itabbam
    1.01
    ৩
    1.00
     современном
    0.99
    POSITIVE LOGITS
    t
    1.85
    in
    1.72
    d
    1.61
     can
    1.51
    s
    1.48
    u
    1.45
    ↵
    1.34
    ton
    1.34
    f
    1.34
    b
    1.27
    Activations Density 0.000%

    No Known Activations