© 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. 36683
    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
    LLI
    0.55
     and
    0.55
     وم
    0.55
    כ
    0.54
     לה
    0.50
     اید
    0.50
    の
    0.50
    وی
    0.50
    ス
    0.50
    ื่อน
    0.50
    POSITIVE LOGITS
     tanning
    0.62
     күзгү
    0.60
     tannin
    0.59
     lycée
    0.59
     பயிற்சி
    0.55
    jaty
    0.55
     細胞
    0.54
     Feria
    0.54
     இயற்க
    0.54
     Kasım
    0.54
    Activations Density 0.000%

    No Known Activations