© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14447
    Prev
    Next
    INDEX
    Explanations

    authentication release latch

    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_13_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
     biru
    0.57
     Birla
    0.54
    '
    0.54
    egar
    0.52
     personnelle
    0.52
    eru
    0.51
     rø
    0.51
    M
    0.51
    d
    0.49
     t
    0.49
    POSITIVE LOGITS
    碾
    0.51
    车
    0.48
     thwarted
    0.47
    清除
    0.46
     उत्‍
    0.46
     ভাগ্যবান
    0.45
     топли
    0.45
    历
    0.45
     Perks
    0.44
     федера
    0.44
    Activations Density 0.019%

    No Known Activations