© 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. 62545
    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
    {
    0.52
    dob
    0.51
    6
    0.48
    growing
    0.47
    p
    0.46
    K
    0.46
    a
    0.46
    ser
    0.46
    t
    0.45
    B
    0.45
    POSITIVE LOGITS
     liberalization
    0.52
    ጭ
    0.52
    ul
    0.48
     guise
    0.48
     తగ్గ
    0.48
     भूमि
    0.48
    anggilan
    0.48
     విడు
    0.47
    व्यों
    0.47
     HOA
    0.47
    Activations Density 0.000%

    No Known Activations