© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77957
    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
    ilus
    0.40
    ategory
    0.40
    बई
    0.38
    spring
    0.37
    語
    0.37
    SPRING
    0.36
    ategori
    0.36
    venus
    0.36
    ido
    0.36
    잊
    0.35
    POSITIVE LOGITS
     buffs
    0.43
     Aw
    0.37
     popcorn
    0.37
    Aw
    0.36
    كين
    0.35
     khăn
    0.35
     sweat
    0.34
     preoccupied
    0.34
     sandpaper
    0.34
     ойнойт
    0.34
    Activations Density 0.000%

    No Known Activations