© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200728
    Prev
    Next
    INDEX
    Explanations

    tilting head with a question

    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_37_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
     такую
    0.45
     TERMS
    0.40
     ত্র
    0.39
     يمكنك
    0.39
     Jens
    0.39
     الكسور
    0.38
    :],
    0.38
    ที่คุณ
    0.38
    揶
    0.38
     आपकी
    0.37
    POSITIVE LOGITS
    左
    0.47
     left
    0.46
     questioned
    0.45
     questioning
    0.41
     deaf
    0.40
     左
    0.39
    に至
    0.39
    衣服
    0.37
    انب
    0.37
    Listening
    0.37
    Activations Density 0.002%

    No Known Activations