© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97317
    Prev
    Next
    INDEX
    Explanations

    ETL process and pipelines

    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_14_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
    א
    0.54
    רי
    0.50
    )–
    0.50
    कॉइन
    0.49
    Фран
    0.49
     workpiece
    0.48
    ﾏ
    0.48
    בּ
    0.48
    ﾌ
    0.47
    नव
    0.46
    POSITIVE LOGITS
    ż
    0.54
     직접
    0.50
    serie
    0.49
    alach
    0.49
     serie
    0.48
     direttamente
    0.48
     veteran
    0.47
     পরিবহন
    0.47
    houses
    0.46
     खेती
    0.46
    Activations Density 0.010%

    No Known Activations