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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 222
    Prev
    Next
    INDEX
    Explanations

    jigsaw puzzles

    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_38_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
    อย่า
    0.42
    糸
    0.38
    Sem
    0.38
    ilgan
    0.38
     counterparts
    0.37
     Sema
    0.36
    semin
    0.36
     আমিন
    0.36
    梳
    0.36
     follows
    0.36
    POSITIVE LOGITS
     puzzles
    1.03
     puzzle
    0.98
    puzzle
    0.98
    Puzzle
    0.93
     puzz
    0.82
     Puzzle
    0.80
     puzzling
    0.75
     jigsaw
    0.69
     jigs
    0.67
     jig
    0.65
    Activations Density 0.007%

    No Known Activations