© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90864
    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
    Testing
    0.44
    )}$,
    0.43
    ברים
    0.43
    保护
    0.42
    เด
    0.41
    يم
    0.41
    Dead
    0.40
    비
    0.40
    Dispose
    0.40
    Uninstall
    0.40
    POSITIVE LOGITS
     united
    0.57
    united
    0.54
     yurt
    0.54
     yr
    0.53
    okar
    0.52
     liked
    0.50
     travelled
    0.49
     union
    0.48
     ได้
    0.48
     Boho
    0.48
    Activations Density 0.000%

    No Known Activations