© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89021
    Prev
    Next
    INDEX
    Explanations

    stroke order

    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_3_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
     Commencez
    0.56
    நபியே
    0.56
    룺
    0.55
     phishing
    0.54
     ہزار
    0.53
     seguenti
    0.53
    udah
    0.52
    帮忙
    0.51
    ¹.
    0.51
     neutrophil
    0.51
    POSITIVE LOGITS
     of
    0.70
    Stock
    0.64
    ↵↵
    0.63
    ’
    0.55
    ของ
    0.54
    ﻬ
    0.54
    Third
    0.54
    Selection
    0.53
    รอ
    0.53
    rown
    0.53
    Activations Density 0.000%

    No Known Activations