© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 15639
    Prev
    Next
    INDEX
    Explanations

    DevExpress, Utah, apps

    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_34_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
    
    0.45
     ませ
    0.40
     Steiner
    0.39
     math
    0.39
     mantras
    0.38
    톄
    0.38
    國民
    0.38
    枥
    0.38
    irge
    0.38
     セット
    0.37
    POSITIVE LOGITS
    Framework
    0.39
    pass
    0.38
    PL
    0.37
    Xcode
    0.37
    Quality
    0.36
    Inspector
    0.36
    Runs
    0.36
    Pass
    0.35
    Mor
    0.35
    ML
    0.35
    Activations Density 0.001%

    No Known Activations