© 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. 15042
    Prev
    Next
    INDEX
    Explanations

    system design and integration

    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
    Negative Logits
    rences
    0.52
    igten
    0.50
    ｋ
    0.50
    igenza
    0.49
    കേന്ദ്രം
    0.49
     Scholarship
    0.49
    withtag
    0.48
    lingen
    0.48
    zechoslovak
    0.48
    ibrant
    0.48
    POSITIVE LOGITS
    मुंबई
    0.61
    嘔
    0.49
     मुंबई
    0.48
     smash
    0.48
     misma
    0.47
    Muscle
    0.47
    Insurance
    0.47
    Hamburg
    0.47
     Tierra
    0.46
     Himalaya
    0.46
    Activations Density 0.069%

    No Known Activations