© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9830
    Prev
    Next
    INDEX
    Explanations

    randomness and chance

    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_13_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
     Mikh
    0.60
     Harus
    0.58
     Букмекердик
    0.57
    󠁮
    0.55
     Букмекерлер
    0.54
     Ig
    0.53
     मेथ
    0.53
     ICR
    0.53
     WWF
    0.52
     Finishing
    0.52
    POSITIVE LOGITS
    Random
    0.62
    random
    0.61
    随机
    0.60
     randomness
    0.58
     hasard
    0.57
     azar
    0.55
     randomize
    0.54
    AppConstant
    0.54
    (
    0.54
     randomly
    0.52
    Activations Density 0.061%

    No Known Activations