© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200848
    Prev
    Next
    INDEX
    Explanations

    say "mode"

    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
     статистика
    0.39
    INGER
    0.38
     $('.
    0.37
    Hosting
    0.37
    峯
    0.36
     (\%)
    0.36
    ラスト
    0.35
     demarcation
    0.35
    睒
    0.35
    किंग
    0.35
    POSITIVE LOGITS
    rect
    0.38
    iune
    0.38
     exploit
    0.38
     Gabe
    0.38
     পূর্ববাংলা
    0.37
     dA
    0.37
    ιάς
    0.37
    ulet
    0.37
     radioButton
    0.37
     provided
    0.36
    Activations Density 0.003%

    No Known Activations