© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 149125
    Prev
    Next
    INDEX
    Explanations

    model

    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_59_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
    課題
    0.65
    Problem
    0.55
    problem
    0.54
     problem
    0.52
     Problem
    0.42
    Node
    0.40
    PROBLEM
    0.40
    ➚
    0.38
    @[
    0.38
    ,​
    0.38
    POSITIVE LOGITS
     busy
    1.02
     Busy
    0.98
    busy
    0.80
    Busy
    0.80
     busiest
    0.69
    忙
    0.67
     ব্যস্ত
    0.66
     busier
    0.66
     व्यस्त
    0.60
     মিলিটারি
    0.47
    Activations Density 0.007%

    No Known Activations