© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18044
    Prev
    Next
    INDEX
    Explanations

    question ending particles

    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_40_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
    ?.
    0.45
    ???
    0.43
    ?>
    0.42
    ????????
    0.41
    isotope
    0.39
     зале
    0.39
    VENUE
    0.38
    ????
    0.38
    ?!
    0.38
    ?
    0.38
    POSITIVE LOGITS
    吗
    1.56
    嗎
    1.54
    了嗎
    1.25
    了吗
    1.20
    ไหม
    1.08
     ли
    1.07
    么
    1.06
    인가
    1.05
    でしょうか
    0.99
    ですか
    0.98
    Activations Density 0.020%

    No Known Activations