© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33917
    Prev
    Next
    INDEX
    Explanations

    compatibility, formats, lifestyles

    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
    cores
    0.42
     Iqbal
    0.40
    স্থলে
    0.40
    厰
    0.38
     kesehatan
    0.37
     dưỡng
    0.37
    健全
    0.37
     ಅನುಪ
    0.37
    Iceland
    0.37
    壊
    0.37
    POSITIVE LOGITS
     quirks
    0.52
     format
    0.48
     incompatibility
    0.47
     Compatible
    0.45
     incompatible
    0.45
     kompat
    0.45
     lifestyles
    0.44
     формат
    0.44
     incompat
    0.44
     formats
    0.44
    Activations Density 0.049%

    No Known Activations