© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84382
    Prev
    Next
    INDEX
    Explanations

    keynote speakers and keywords

    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_0_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
    n
    2.36
    ad
    2.16
    u
    2.02
    it
    1.62
    g
    1.59
     It
    1.58
    er
    1.57
    is
    1.57
    ul
    1.56
    ing
    1.55
    POSITIVE LOGITS
    ро
    1.72
     trwa
    1.46
    ા
    1.35
    ۰
    1.31
    した
    1.27
    ד
    1.27
    ご紹介
    1.25
    ா
    1.23
     ສຳ
    1.23
    ຈັດສົ່ງ
    1.23
    Activations Density 0.000%

    No Known Activations