© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21704
    Prev
    Next
    INDEX
    Explanations

    lay

    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_56_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
    挙
    0.46
     laid
    0.43
     lays
    0.42
    舉
    0.41
    거
    0.39
    чета
    0.38
     거
    0.38
    Freel
    0.38
    ऱ्यांना
    0.37
     LAY
    0.37
    POSITIVE LOGITS
    복
    0.43
    fors
    0.42
     believe
    0.41
     hands
    0.40
     분포
    0.37
    opener
    0.37
    피
    0.37
    believe
    0.37
     düşük
    0.37
    算的
    0.37
    Activations Density 0.011%

    No Known Activations