© 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
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37130
    Prev
    Next
    INDEX
    Explanations

    Vietnamese phonemes

    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_57_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
     du
    0.86
     Du
    0.67
    Du
    0.65
    du
    0.56
     ma
    0.55
     ду
    0.55
    杜
    0.54
     ta
    0.43
    duplicated
    0.43
     tí
    0.42
    POSITIVE LOGITS
     chu
    1.29
     Chu
    1.13
    Chu
    1.13
    chu
    1.04
     ph
    0.85
    CHU
    0.83
    楚
    0.76
     чу
    0.75
     FP
    0.72
     fp
    0.65
    Activations Density 0.002%

    No Known Activations