© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245990
    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_40_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
     Contemporary
    0.40
    的路
    0.39
     tableView
    0.38
     czyn
    0.38
     tbl
    0.38
     ы
    0.37
    Contemporary
    0.37
     κάνει
    0.37
    ଇ
    0.37
    elli
    0.37
    POSITIVE LOGITS
    stoffe
    0.37
    もちゃ
    0.37
    bod
    0.36
    Satisf
    0.35
    hang
    0.34
     satisf
    0.34
    dió
    0.34
    CCOCC
    0.34
     گاز
    0.34
    स्पति
    0.33
    Activations Density 0.000%

    No Known Activations