© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36286
    Prev
    Next
    INDEX
    Explanations

    proceed with caution

    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_3_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
     I
    0.89
    é
    0.78
    t
    0.77
    em
    0.75
    :
    0.70
    o
    0.67
    II
    0.66
    en
    0.65
    h
    0.65
    I
    0.65
    POSITIVE LOGITS
     proced
    0.89
     procéd
    0.87
     процеду
    0.86
    手続き
    0.78
    ف
    0.76
     procedure
    0.75
    手順
    0.74
     proceeds
    0.74
     procédure
    0.72
    日閲覧
    0.72
    Activations Density 0.001%

    No Known Activations