© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90308
    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_11_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
     ello
    0.47
     Thé
    0.47
     [:
    0.46
     fatorial
    0.45
     Bernoulli
    0.44
     নিউ
    0.44
     TREE
    0.44
    !--
    0.43
     মূর্তি
    0.43
    Appendix
    0.42
    POSITIVE LOGITS
    FieldContext
    0.47
    茫
    0.47
    boy
    0.44
     بز
    0.44
    lineContainer
    0.42
    ்கள்
    0.41
    browserTarget
    0.41
     நடைபெற்றது
    0.40
     خدمات
    0.40
    czyn
    0.40
    Activations Density 0.000%

    No Known Activations