© 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. 16141
    Prev
    Next
    INDEX
    Explanations

    gem setting or stones

    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
    গ্ন
    0.40
    SOURCES
    0.40
    톄
    0.39
    glide
    0.38
    вшим
    0.36
     Chromat
    0.35
     সেরে
    0.35
     Hog
    0.35
    azor
    0.35
    伤
    0.35
    POSITIVE LOGITS
     studded
    1.03
    studded
    0.83
     set
    0.80
     embedded
    0.78
    鑲
    0.78
     embed
    0.77
    镶
    0.73
     embedding
    0.73
     inlaid
    0.72
     diamond
    0.71
    Activations Density 0.029%

    No Known Activations