© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 136724
    Prev
    Next
    INDEX
    Explanations

    Thai words starting with อ

    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_37_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
     सलू
    0.51
     පිළ
    0.41
    setlength
    0.41
     hasht
    0.39
    嬂
    0.39
    ują
    0.38
    ując
    0.38
     takePhotoButton
    0.38
    团
    0.38
    platte
    0.37
    POSITIVE LOGITS
    ële
    0.39
     exciting
    0.36
    Sprintf
    0.35
     amid
    0.35
    Amid
    0.35
     অতীত
    0.33
    ARIA
    0.33
    Anything
    0.33
     Cheapest
    0.33
    যাত্রা
    0.33
    Activations Density 0.000%

    No Known Activations