© 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. 45995
    Prev
    Next
    INDEX
    Explanations

    Michael Jackson

    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
    れる
    0.49
     probar
    0.48
     glandular
    0.47
    ");
    0.47
     реша
    0.46
     добы
    0.46
    一支
    0.46
    y
    0.46
     ग़
    0.46
     й
    0.46
    POSITIVE LOGITS
    有沒有
    0.56
    ঁচা
    0.56
     consigo
    0.55
     Managers
    0.54
    မ့်
    0.53
     void
    0.53
     엔
    0.53
    managers
    0.52
    Managers
    0.51
     Enrique
    0.50
    Activations Density 0.000%

    No Known Activations