© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198959
    Prev
    Next
    INDEX
    Explanations

    oilskin coat, scroll height

    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_12_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
    ﯿ
    0.60
    ﺮ
    0.57
    관
    0.56
    جست
    0.55
     Aseg
    0.54
    ంచి
    0.54
    pengaruhi
    0.52
    ン
    0.50
    katan
    0.50
    نش
    0.49
    POSITIVE LOGITS
     แต่
    0.60
     jednu
    0.56
     prawns
    0.55
     zippers
    0.54
    แต่
    0.53
     зру
    0.53
     বজ্র
    0.52
     但
    0.52
     holster
    0.51
     време
    0.51
    Activations Density 0.010%

    No Known Activations