© 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. 6490
    Prev
    Next
    INDEX
    Explanations

    os.listdir

    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
     शी
    0.37
     Zad
    0.37
    保証
    0.36
     ret
    0.36
     zap
    0.35
     localized
    0.35
     جعل
    0.35
    锯
    0.34
    cci
    0.34
    cc
    0.34
    POSITIVE LOGITS
     Stat
    0.60
    Stat
    0.57
    system
    0.57
     stat
    0.56
    stat
    0.54
     system
    0.52
    システム
    0.51
    STAT
    0.50
     시스템
    0.50
     سسٹم
    0.48
    Activations Density 0.004%

    No Known Activations