© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 864
    Prev
    Next
    INDEX
    Explanations

    test.testing

    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
    Negative Logits
     بتا
    0.40
     अमर
    0.39
     الجمه
    0.39
    愪
    0.39
    ﮗ
    0.39
     disparition
    0.39
    𝓎
    0.39
     결방
    0.37
    ])$.
    0.37
     സമര
    0.37
    POSITIVE LOGITS
    TEST
    0.52
     test
    0.50
     tester
    0.50
    test
    0.49
     TEST
    0.46
     tested
    0.46
     тестирование
    0.46
     Test
    0.45
     testers
    0.44
    测试
    0.44
    Activations Density 0.001%

    No Known Activations