© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5937
    Prev
    Next
    INDEX
    Explanations

    articles and phrases

    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_40_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
     jaoks
    0.77
     için
    0.75
     యొక్క
    0.75
     icin
    0.73
    साठी
    0.72
    에
    0.70
     में
    0.68
    への
    0.67
    কে
    0.66
     থেকে
    0.65
    POSITIVE LOGITS
     얻
    0.43
     teniendo
    0.41
     단순히
    0.41
     있는데
    0.40
     doğrudan
    0.40
     Which
    0.39
    まして
    0.39
     সরাসরি
    0.38
    あくまで
    0.38
     가지고
    0.38
    Activations Density 0.015%

    No Known Activations