© 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. 88907
    Prev
    Next
    INDEX
    Explanations

    for nothing or for reference

    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
    n
    0.98
    使用
    0.78
    ش
    0.72
    time
    0.71
    ü
    0.71
    name
    0.71
    ?
    0.70
    li
    0.66
    mid
    0.66
    时间
    0.66
    POSITIVE LOGITS
    {//
    0.76
    芾
    0.67
    িন
    0.67
    uje
    0.66
     없다
    0.66
     divulg
    0.63
    िफिकेट
    0.61
    рие
    0.61
     recib
    0.61
    riendo
    0.60
    Activations Density 0.001%

    No Known Activations