© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112836
    Prev
    Next
    INDEX
    Explanations

    Japanese suffixes and related names

    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_2_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
    ER
    1.03
    ने
    0.88
     lahat
    0.86
    ING
    0.84
    한
    0.80
     نمایند
    0.79
    EN
    0.79
    er
    0.78
    AR
    0.78
    વો
    0.76
    POSITIVE LOGITS
    ى
    1.21
    あります
    1.08
    1
    0.99
    ır
    0.96
    ري
    0.95
    lük
    0.93
    н
    0.92
    وم
    0.86
    ны
    0.86
    к
    0.86
    Activations Density 0.012%

    No Known Activations