© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52091
    Prev
    Next
    INDEX
    Explanations

    can be assigned

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     involution
    0.30
    呯
    0.29
    bn
    0.27
     ലക്ഷ
    0.26
     पैकिंग
    0.26
    ভিক্ষ
    0.25
    աշ
    0.25
    
    0.25
     Inbetriebnahme
    0.25
    ंट
    0.25
    POSITIVE LOGITS
    Kak
    0.28
    グリ
    0.28
    Holding
    0.26
     पाठ
    0.25
    راع
    0.25
    Metering
    0.25
     pizarra
    0.25
    Assign
    0.25
     Brant
    0.25
    Memo
    0.24
    Activations Density 0.005%

    No Known Activations