© 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. 166289
    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
    诖
    0.33
     distal
    0.32
     σχ
    0.32
    鍱
    0.31
     Sediment
    0.30
     penetrating
    0.29
    仠
    0.29
    郅
    0.29
    ഷ്ട
    0.28
    શ્મી
    0.28
    POSITIVE LOGITS
     caballero
    0.31
    Geometry
    0.28
     trece
    0.27
    帮
    0.27
    lac
    0.27
    Occ
    0.26
     rej
    0.26
    抬
    0.26
     magicians
    0.26
    erb
    0.26
    Activations Density 0.000%

    No Known Activations