© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48713
    Prev
    Next
    INDEX
    Explanations

    repeating actions

    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_55_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
    elleen
    0.38
    ότη
    0.37
    ➀
    0.37
    园
    0.36
     }}$
    0.36
    ヤモンド
    0.35
     誕生日
    0.35
    рик
    0.35
     理
    0.35
    理
    0.34
    POSITIVE LOGITS
     straining
    0.49
     repeating
    0.49
     memor
    0.47
     silent
    0.47
     teased
    0.46
     pores
    0.45
     Memor
    0.45
     tease
    0.45
     memorandum
    0.44
     teasing
    0.44
    Activations Density 0.016%

    No Known Activations