© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129606
    Prev
    Next
    INDEX
    Explanations

    U terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     фа
    0.47
    位相
    0.41
     velit
    0.41
    vel
    0.39
    afel
    0.39
     assisting
    0.39
    cepc
    0.39
    相
    0.39
    絬
    0.39
     Affairs
    0.38
    POSITIVE LOGITS
     Méd
    0.46
    Fol
    0.42
    idenza
    0.41
    bear
    0.40
    henius
    0.40
    Dana
    0.39
    middleware
    0.38
    Bear
    0.38
     bear
    0.38
    Méd
    0.38
    Activations Density 0.016%

    No Known Activations