© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111630
    Prev
    Next
    INDEX
    Explanations

    àn mi

    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_2_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
    D
    1.17
    N
    1.09
    ↵
    1.05
    M
    1.02
    P
    0.99
     불구하고
    0.97
    L
    0.92
    F
    0.88
    R
    0.86
    。
    0.85
    POSITIVE LOGITS
    n
    2.03
    re
    1.73
    น
    1.54
    리
    1.53
    ul
    1.52
    ת
    1.49
    ри
    1.48
    트
    1.47
    ни
    1.45
    j
    1.45
    Activations Density 0.000%

    No Known Activations