© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51705
    Prev
    Next
    INDEX
    Explanations

    say ordinal suffixes

    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_55_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
    preferred
    0.42
    が出る
    0.39
    対応
    0.37
     españoles
    0.37
    དང་
    0.36
    menubar
    0.36
    톡
    0.35
     চু
    0.34
    붙
    0.34
    より
    0.34
    POSITIVE LOGITS
     從
    0.37
     MAIN
    0.36
     从
    0.36
     Proof
    0.36
     UPPER
    0.36
    ème
    0.35
     ஆம்
    0.35
    克斯
    0.35
    Ν
    0.34
     प्रूफ
    0.34
    Activations Density 0.000%

    No Known Activations