© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86603
    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_18_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
     نیشنل
    0.48
     Would
    0.46
    ള
    0.46
    地に
    0.46
     perilous
    0.45
     Medi
    0.44
     occurring
    0.44
     Route
    0.44
    用意
    0.43
    並不
    0.43
    POSITIVE LOGITS
     čís
    0.57
    ar
    0.52
     humaines
    0.52
    Parse
    0.50
    ש
    0.50
    মানব
    0.49
    shear
    0.49
    ill
    0.48
    online
    0.48
    exercice
    0.48
    Activations Density 0.000%

    No Known Activations