© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30740
    Prev
    Next
    INDEX
    Explanations

    lists of specific items or concepts

    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_31_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
     résult
    0.40
    ቅ
    0.38
     Tos
    0.37
     MPC
    0.37
     trong
    0.36
     Hail
    0.36
    جهة
    0.36
     exced
    0.35
     exceeding
    0.35
    Tes
    0.35
    POSITIVE LOGITS
    scriptsize
    0.36
    footnotesize
    0.35
    릿
    0.34
    一只
    0.33
     জড়িত
    0.33
    _="
    0.33
    哒
    0.33
    alin
    0.32
    都要
    0.32
    lementine
    0.31
    Activations Density 0.045%

    No Known Activations