© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4476
    Prev
    Next
    INDEX
    Explanations

    match/matching

    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_40_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
     permutation
    0.44
     جاری
    0.42
    ഷേ
    0.42
    signature
    0.39
    续
    0.39
    िटर
    0.36
     샤
    0.35
    Signature
    0.35
    샤
    0.35
    iedy
    0.35
    POSITIVE LOGITS
     matched
    0.85
     Matching
    0.83
    matched
    0.83
     matching
    0.82
    matching
    0.78
    Matching
    0.77
     Match
    0.76
     match
    0.76
    匹配
    0.73
    match
    0.72
    Activations Density 0.000%

    No Known Activations