© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    梢
    0.42
     FUNCTION
    0.42
    却是
    0.41
     calorimeter
    0.41
     функ
    0.40
     Funktion
    0.40
     функция
    0.39
     ფუნქ
    0.38
     crops
    0.38
     നിറ
    0.37
    POSITIVE LOGITS
    een
    0.41
    main
    0.40
    lot
    0.39
    主
    0.37
    unen
    0.37
    otri
    0.37
    typescript
    0.37
    son
    0.36
    ein
    0.36
     zelf
    0.36
    Activations Density 0.000%

    No Known Activations