© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206134
    Prev
    Next
    INDEX
    Explanations

    Marcus by Goldman Sachs

    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_19_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
     Himal
    0.46
     Mistakes
    0.43
     Tarifleri
    0.43
     }{
    0.42
     YA
    0.42
     вроде
    0.41
     આજ
    0.41
     luminoso
    0.41
    Allow
    0.41
     "*.
    0.41
    POSITIVE LOGITS
    ponding
    0.48
     ସ
    0.46
    rés
    0.45
     Jeh
    0.44
     sécurité
    0.43
    lors
    0.43
    وده
    0.43
    čení
    0.43
    Jeh
    0.43
     جنگ
    0.42
    Activations Density 0.000%

    No Known Activations