© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41742
    Prev
    Next
    INDEX
    Explanations

    divisibility checks starting from 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     micrograph
    0.40
    Session
    0.39
    gw
    0.39
     slope
    0.38
    ၢ
    0.38
     vanes
    0.37
     Benton
    0.37
     চিহ্নিত
    0.37
    mixing
    0.37
     Sinai
    0.36
    POSITIVE LOGITS
    вин
    0.42
     cenário
    0.38
    લાક
    0.37
    Witt
    0.37
     گزشتہ
    0.37
    馳
    0.37
     सामने
    0.36
     子
    0.36
     retos
    0.36
     उसमें
    0.35
    Activations Density 0.001%

    No Known Activations