© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27685
    Prev
    Next
    INDEX
    Explanations

    `127.0.0.1`

    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_10_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
    一系列
    0.75
     frumo
    0.65
     vincul
    0.64
     consomm
    0.64
    คณะ
    0.63
     planej
    0.62
    R
    0.62
     बढ़ते
    0.62
     către
    0.61
     می‌کنند
    0.61
    POSITIVE LOGITS
     of
    0.71
     are
    0.68
    ਾ
    0.67
    ى
    0.66
    u
    0.64
    า
    0.63
    া
    0.62
    و
    0.61
    。
    0.61
    ре
    0.58
    Activations Density 0.004%

    No Known Activations