© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50944
    Prev
    Next
    INDEX
    Explanations

    dust motes danced

    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_31_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
     Hà
    0.31
    ැ
    0.30
     traverse
    0.29
     Aes
    0.28
     Buccaneers
    0.28
    ককে
    0.28
     grace
    0.27
     केमिक
    0.27
     Railroad
    0.27
     Grace
    0.27
    POSITIVE LOGITS
    哪
    0.29
     দিল
    0.28
     maxi
    0.28
    margins
    0.28
    नाम
    0.28
    篮
    0.28
    ඨ
    0.28
    甕
    0.27
    Neil
    0.27
     امن
    0.27
    Activations Density 0.031%

    No Known Activations