© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16593
    Prev
    Next
    INDEX
    Explanations

    speed

    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_15_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
     ツ
    0.68
    ępu
    0.57
    ắ
    0.56
     الكامل
    0.55
    naire
    0.54
     ແ
    0.53
    కరించ
    0.53
     然后
    0.53
    អ្វី
    0.53
     Ừ
    0.53
    POSITIVE LOGITS
        
    0.56
     they
    0.50
     waterproof
    0.48
     plasma
    0.45
     slimy
    0.45
     treating
    0.45
     heater
    0.45
     dito
    0.44
     .
    0.44
     vessel
    0.44
    Activations Density 0.001%

    No Known Activations