© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51082
    Prev
    Next
    INDEX
    Explanations

    random or surprise me

    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_31_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
     粉
    0.36
    rition
    0.35
     မိ
    0.34
    ्यूब
    0.34
    ტიკ
    0.34
    ශ්‍ය
    0.33
     гало
    0.33
    욤
    0.33
     pouvoirs
    0.33
     تكعيب
    0.33
    POSITIVE LOGITS
     random
    0.82
     Random
    0.71
    random
    0.69
     serendip
    0.67
    Random
    0.65
    随机
    0.64
     unplanned
    0.61
     randomly
    0.57
     랜덤
    0.57
     surprise
    0.53
    Activations Density 0.192%

    No Known Activations