© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5228
    Prev
    Next
    INDEX
    Explanations

    ruby programming language

    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
    FileInputExcel
    0.44
     resources
    0.43
    资源的
    0.43
    বিধা
    0.40
     FIF
    0.40
     self
    0.39
    DICT
    0.39
    ઠ
    0.39
     ресурсы
    0.38
     Fif
    0.37
    POSITIVE LOGITS
     Head
    0.40
     VM
    0.38
     Fro
    0.37
    LAN
    0.36
     Indem
    0.36
    Head
    0.35
     insider
    0.35
    vish
    0.35
    鸷
    0.34
     genre
    0.34
    Activations Density 0.001%

    No Known Activations