© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4429
    Prev
    Next
    INDEX
    Explanations

    Korea and Seoul websites

    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_39_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
     giấy
    0.42
     प्रोजेक्ट
    0.41
    坏
    0.41
    REGIUNE
    0.41
     ikan
    0.41
    ण्ट
    0.40
    ার্জি
    0.40
    েমনি
    0.39
     игре
    0.39
    قیق
    0.39
    POSITIVE LOGITS
     관련
    0.53
     한국
    0.45
    related
    0.44
     서울
    0.43
     대한
    0.43
     공
    0.42
     законода
    0.42
     대한민국
    0.41
     평가
    0.40
    相关
    0.40
    Activations Density 0.008%

    No Known Activations