© 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. 213517
    Prev
    Next
    INDEX
    Explanations

    Dungeons & Dragons

    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
    靑
    0.40
     Qing
    0.39
     группа
    0.37
     Thanh
    0.37
    qing
    0.37
     Lý
    0.37
    オー
    0.36
    Moj
    0.36
     Toch
    0.36
    向
    0.36
    POSITIVE LOGITS
    hur
    0.43
    aru
    0.40
    cp
    0.40
    dlg
    0.39
    indoor
    0.39
     hur
    0.39
    Württemberg
    0.38
     HUR
    0.38
    uix
    0.37
     Dix
    0.37
    Activations Density 0.000%

    No Known Activations