© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54139
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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
    詞
    0.34
    жей
    0.33
     вино
    0.33
     Yol
    0.33
     दाखल
    0.32
     لفظ
    0.32
     कारो
    0.32
    闥
    0.31
    輝
    0.31
     Drag
    0.31
    POSITIVE LOGITS
     random
    0.60
    random
    0.57
    Random
    0.57
     randomness
    0.52
    随机
    0.50
     randomization
    0.49
     Random
    0.48
     randomly
    0.46
     RANDOM
    0.45
     rand
    0.43
    Activations Density 0.003%

    No Known Activations