© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 140692
    Prev
    Next
    INDEX
    Explanations

    control

    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_46_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
     efficiency
    0.43
    效率
    0.41
     value
    0.41
    効率
    0.41
     values
    0.41
     Efficiency
    0.41
     efficiencies
    0.40
    綀
    0.40
     eficiencia
    0.40
     eficiência
    0.40
    POSITIVE LOGITS
     law
    0.62
    law
    0.59
    法
    0.55
    Law
    0.54
     Law
    0.52
     LAW
    0.49
     القانون
    0.48
    LAW
    0.47
     कानून
    0.47
    법
    0.45
    Activations Density 0.001%

    No Known Activations