© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63052
    Prev
    Next
    INDEX
    Explanations

    Roman pasta dishes

    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_46_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
    াদ
    0.41
    োদন
    0.41
    ixir
    0.40
    •
    0.39
     sherry
    0.37
     Schell
    0.37
    蟄
    0.37
    Ｄ
    0.36
    ǘ
    0.36
     রহমানের
    0.36
    POSITIVE LOGITS
    ユ
    0.55
     Tat
    0.44
    Tatar
    0.43
    육
    0.42
     tat
    0.42
    Lea
    0.42
     Lea
    0.42
    Tat
    0.40
    레
    0.40
     Tart
    0.39
    Activations Density 0.013%

    No Known Activations