© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29222
    Prev
    Next
    INDEX
    Explanations

    pattern recognition

    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_10_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
     to
    0.59
     by
    0.57
     k
    0.55
     v
    0.53
    ),
    0.53
    AT
    0.52
     at
    0.49
     b
    0.48
    >,
    0.48
     is
    0.48
    POSITIVE LOGITS
    Patterns
    0.97
    Pattern
    0.91
     Patterns
    0.91
    pattern
    0.88
     패턴
    0.86
     Pattern
    0.78
    patterns
    0.75
     patterns
    0.74
     pattern
    0.73
    柄
    0.71
    Activations Density 0.067%

    No Known Activations