© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34190
    Prev
    Next
    INDEX
    Explanations

    Korean language

    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_50_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
    නව
    0.46
     statistically
    0.38
     raya
    0.38
    ဥ
    0.38
     bata
    0.37
     QtWidgets
    0.37
    كا
    0.37
    वत्ता
    0.37
    ዐ
    0.37
     Bat
    0.36
    POSITIVE LOGITS
    Yon
    0.59
     Yon
    0.54
    AES
    0.48
    িব
    0.45
    Aes
    0.44
     AES
    0.44
     yon
    0.41
    中国人
    0.41
    AE
    0.41
     Aes
    0.41
    Activations Density 0.002%

    No Known Activations