© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170204
    Prev
    Next
    INDEX
    Explanations

    measures on sets (Σ)

    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_20_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
     płyt
    0.24
    ؘ
    0.24
     उद्योग
    0.23
     Newport
    0.22
     właścic
    0.21
     सुरक्षा
    0.21
    throat
    0.21
    }}{
    0.21
    MAN
    0.21
    安全
    0.21
    POSITIVE LOGITS
    FrameworkElement
    0.25
     agrarian
    0.25
     indoct
    0.24
     indeterm
    0.23
     цих
    0.23
     circa
    0.23
     destes
    0.22
     индиви
    0.22
     Вікі
    0.22
    க்களை
    0.22
    Activations Density 0.002%

    No Known Activations