© 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. 225245
    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
    曱
    0.59
     évén
    0.55
    mtrl
    0.55
    зме
    0.55
    AIRMAN
    0.52
    \|_{\
    0.52
    ઉસ
    0.51
    rawData
    0.51
    ẫn
    0.51
    🗯
    0.51
    POSITIVE LOGITS
     swap
    0.54
     small
    0.50
     positive
    0.49
     bishop
    0.49
    +
    0.49
    )
    0.47
     miss
    0.46
     car
    0.46
    :
    0.46
    ar
    0.46
    Activations Density 0.000%

    No Known Activations