© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65377
    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_41_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
    ouge
    0.38
    computing
    0.37
     rãi
    0.37
    섰
    0.37
    NHS
    0.37
    oxide
    0.36
    ismer
    0.35
    暁
    0.35
    दलीय
    0.35
     궁
    0.34
    POSITIVE LOGITS
     elevation
    2.23
     Elevation
    2.14
    Elevation
    2.03
     elevations
    1.97
    elevation
    1.85
     Elevations
    1.84
     Elev
    1.73
     elev
    1.72
     elevate
    1.69
    Elev
    1.66
    Activations Density 0.004%

    No Known Activations