© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50332
    Prev
    Next
    INDEX
    Explanations

    LeetCode 1 Two Sum

    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_30_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
    CPU
    0.33
     መሳሪያ
    0.33
    เดินทาง
    0.32
     মুক্তিবাহিনী
    0.32
    <0xB0>
    0.32
     Γερμαν
    0.31
    ellingen
    0.30
    сів
    0.30
    ṯ
    0.30
    emans
    0.30
    POSITIVE LOGITS
    穹
    0.39
     পদ্
    0.39
     रिट
    0.37
    brigen
    0.34
    我又
    0.34
     Novak
    0.33
     নব
    0.33
     Suddenly
    0.33
    入
    0.33
    紧
    0.33
    Activations Density 0.001%

    No Known Activations