© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146236
    Prev
    Next
    INDEX
    Explanations

    say padding

    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_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     P
    0.89
     pă
    0.65
     ప
    0.63
     پ
    0.57
     pais
    0.53
     pás
    0.53
     patches
    0.52
     pâ
    0.52
    P
    0.52
     พ
    0.52
    POSITIVE LOGITS
    Ps
    0.69
     Ps
    0.68
    Pe
    0.65
    Ph
    0.64
     Pen
    0.62
    Peter
    0.62
    Pr
    0.61
    彭
    0.61
     По
    0.61
    Pen
    0.60
    Activations Density 0.005%

    No Known Activations