© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68647
    Prev
    Next
    INDEX
    Explanations

    Thai diacritics

    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_51_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
    ື
    0.51
    ือด
    0.45
     Obs
    0.40
    IOD
    0.38
    Obs
    0.38
    ืน
    0.38
     justifies
    0.38
     Traff
    0.38
     trafficking
    0.36
    WALLET
    0.35
    POSITIVE LOGITS
    ่
    0.65
    ່ມ
    0.64
    ່
    0.58
    ่อ
    0.57
    ່ນ
    0.54
    ู่
    0.52
    ่น
    0.50
    ่ว
    0.48
     ù
    0.48
    ่ม
    0.47
    Activations Density 0.008%

    No Known Activations