© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91108
    Prev
    Next
    INDEX
    Explanations

    pattern matching

    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_60_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
    Pattern
    0.64
    Patterns
    0.63
    Page
    0.57
    Last
    0.57
    Le
    0.57
    Pat
    0.55
    e
    0.55
    pattern
    0.55
    Part
    0.54
    2
    0.54
    POSITIVE LOGITS
     match
    0.66
     Match
    0.63
     맞
    0.61
     import
    0.55
     मैच
    0.54
     imports
    0.54
     matchs
    0.53
    マッチ
    0.53
     matchups
    0.51
     m
    0.51
    Activations Density 0.003%

    No Known Activations