© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53075
    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_31_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
     desn
    0.39
    Chemistry
    0.38
    Advertisement
    0.38
    氚
    0.38
     Foro
    0.37
    IRS
    0.37
    irts
    0.36
     thermometers
    0.36
     entrevist
    0.36
    Vendor
    0.35
    POSITIVE LOGITS
     suspend
    0.38
     मंत्रिपरिषद
    0.37
    睡眠
    0.37
     CGSize
    0.36
     bescherm
    0.36
     morality
    0.36
    idoarjo
    0.35
    )}_{
    0.34
    保护
    0.34
     इधर
    0.34
    Activations Density 0.000%

    No Known Activations