© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140376
    Prev
    Next
    INDEX
    Explanations

    distribution

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    पू
    0.40
    公平
    0.39
    涌
    0.38
     PURCHASE
    0.38
     Corb
    0.38
    masına
    0.38
    తా
    0.38
     Sở
    0.38
    स्रोत
    0.38
    龅
    0.38
    POSITIVE LOGITS
     distribution
    0.61
     Distribution
    0.54
     распреде
    0.54
     توزيع
    0.52
     distribute
    0.51
    Distribution
    0.51
     allocation
    0.51
     algorithm
    0.49
    distribution
    0.49
     distributing
    0.49
    Activations Density 0.002%

    No Known Activations