© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 3803
    Prev
    Next
    INDEX
    Explanations

    performance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    VIII
    0.41
    劍
    0.39
    ایج
    0.39
     viii
    0.38
     xii
    0.38
    ➌
    0.38
    gold
    0.38
    Oliv
    0.37
    sword
    0.37
     زيت
    0.37
    POSITIVE LOGITS
     performance
    0.51
     allocation
    0.43
     finite
    0.40
     Sugar
    0.40
     perf
    0.39
     R
    0.38
     desempeño
    0.38
    性能
    0.38
     fina
    0.38
     pou
    0.38
    Activations Density 0.056%

    No Known Activations