© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206373
    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_10_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
     integrals
    0.53
     commutes
    0.52
     auta
    0.51
     dě
    0.49
     malls
    0.49
     agonists
    0.49
     τ
    0.48
     temples
    0.48
     invoices
    0.48
     sinks
    0.48
    POSITIVE LOGITS
    гра
    0.49
    旅
    0.49
    unprocessable
    0.47
    亚博
    0.47
    不
    0.46
    opter
    0.46
    飞机
    0.45
    飞行
    0.44
    了
    0.44
    故事
    0.44
    Activations Density 0.000%

    No Known Activations