© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204976
    Prev
    Next
    INDEX
    Explanations

    trader"""

    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
    ାନ
    0.41
    icmp
    0.37
     spheroid
    0.37
     مطم
    0.37
    ற்ற
    0.36
    ʟ
    0.35
     liberd
    0.35
     corz
    0.35
     Infinite
    0.34
     الصغيرة
    0.34
    POSITIVE LOGITS
     Trader
    0.43
    Trader
    0.42
    䒿
    0.39
     ч
    0.39
    凖
    0.38
     trader
    0.38
     ਜ
    0.38
    țial
    0.38
     traders
    0.37
     Traders
    0.37
    Activations Density 0.000%

    No Known Activations