© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206054
    Prev
    Next
    INDEX
    Explanations

    next followed by event/time

    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_20_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
    ³.
    0.43
     ď
    0.43
    (_.
    0.42
    ittä
    0.41
     ?.
    0.41
     でしょう
    0.41
    ď
    0.41
     authenticate
    0.41
    שה
    0.40
     benc
    0.39
    POSITIVE LOGITS
    حم
    0.50
     phosphat
    0.44
    Winters
    0.44
     ఖ
    0.42
     Schweizer
    0.41
     لخ
    0.41
     श्रम
    0.40
     imprint
    0.40
    劳动
    0.40
    哲学
    0.40
    Activations Density 0.001%

    No Known Activations