© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6989
    Prev
    Next
    INDEX
    Explanations

    sparse categorical cross

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Duane
    0.41
    മിതി
    0.39
    amnă
    0.38
    ゲーム
    0.38
    Мне
    0.38
    istration
    0.37
    ￡
    0.35
    ιν
    0.35
     inverter
    0.35
    fordert
    0.34
    POSITIVE LOGITS
     sparse
    0.70
     dense
    0.68
     Dense
    0.66
    sparse
    0.61
    dense
    0.61
    Dense
    0.58
     dens
    0.58
     Sparse
    0.58
    Sparse
    0.54
    Dens
    0.53
    Activations Density 0.000%

    No Known Activations