© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14971
    Prev
    Next
    INDEX
    Explanations

    tells what something is

    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
     与
    0.65
     eroded
    0.61
     Czar
    0.60
    дт
    0.59
    铁路
    0.59
     değeri
    0.59
     ABSORBED
    0.57
     cz
    0.56
    🧤
    0.56
     Mussolini
    0.56
    POSITIVE LOGITS
    re
    0.70
    is
    0.63
    tho
    0.63
    Level
    0.62
    Software
    0.61
    Emple
    0.61
    F
    0.60
    for
    0.59
    free
    0.58
    mys
    0.56
    Activations Density 0.048%

    No Known Activations