© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28386
    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_40_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
     Toda
    0.37
     hectares
    0.37
     Thunderbolt
    0.36
     Convex
    0.36
    氅
    0.36
    糰
    0.35
     Chunk
    0.35
     Tester
    0.35
     Rectangle
    0.35
     rectangle
    0.34
    POSITIVE LOGITS
    ايبي
    0.37
     دوا
    0.37
    }_{-
    0.36
     contentView
    0.36
     lī
    0.35
     cufflinks
    0.35
    Ham
    0.35
    ;}
    0.35
    ایر
    0.35
    দাতা
    0.34
    Activations Density 0.000%

    No Known Activations