© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101311
    Prev
    Next
    INDEX
    Explanations

    play on words

    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_14_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
     asli
    0.67
     yuè
    0.57
     zipper
    0.55
     autoplay
    0.55
    瑋
    0.54
     insistence
    0.54
     xj
    0.54
     gird
    0.52
     JOH
    0.52
     lên
    0.52
    POSITIVE LOGITS
    Japan
    0.65
    م
    0.65
    leq
    0.55
    LONDON
    0.55
    japan
    0.54
     مسجد
    0.53
    Sweden
    0.53
    Get
    0.52
    England
    0.51
    Ду
    0.51
    Activations Density 0.000%

    No Known Activations