© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195614
    Prev
    Next
    INDEX
    Explanations

    technical terms or code

    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_50_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
    त्मक
    0.98
    एं
    0.82
    ત્મક
    0.81
    ğı
    0.80
    एँ
    0.77
    ぁ
    0.74
    ĵo
    0.72
    şı
    0.71
    ρχ
    0.71
    வுக்கு
    0.71
    POSITIVE LOGITS
    ों
    0.78
    ରେ
    0.57
    ਾਂ
    0.57
    َا
    0.57
    ระหว่าง
    0.54
    އ
    0.54
    ぅ
    0.54
    ই
    0.53
    ව
    0.53
    Ы
    0.52
    Activations Density 0.003%

    No Known Activations