© 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. 159031
    Prev
    Next
    INDEX
    Explanations

    fiscal year

    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
    金融
    0.51
     금융
    0.46
     Banc
    0.39
     Бен
    0.38
    的金
    0.38
    ޭ
    0.37
     cabaret
    0.37
     quadratic
    0.36
    ወዳ
    0.36
    nominated
    0.36
    POSITIVE LOGITS
    財
    1.08
    재
    0.88
    财
    0.81
     재
    0.77
     Re
    0.73
    Re
    0.70
    昛
    0.69
     ре
    0.58
     Tài
    0.52
     tài
    0.52
    Activations Density 0.000%

    No Known Activations