© 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. 46680
    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
     Hazards
    0.47
     has
    0.47
     Care
    0.46
    ?
    0.45
     Access
    0.45
     Police
    0.45
     Spectra
    0.45
     Detective
    0.45
     daarna
    0.44
     Academy
    0.44
    POSITIVE LOGITS
     एमसीक्यू
    0.52
    初心
    0.51
    iją
    0.50
     コン
    0.49
    _="
    0.49
    =");
    0.49
     Един
    0.48
     گرف
    0.47
    を用意
    0.47
    𝙔
    0.47
    Activations Density 0.000%

    No Known Activations