© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3941
    Prev
    Next
    INDEX
    Explanations

    matlab code snippets

    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_39_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
    orian
    0.46
     Кли
    0.39
    បញ្ចប់
    0.38
    ग्राहक
    0.38
     রঙ
    0.37
    컥
    0.37
    неопр
    0.37
    푀
    0.36
    报价
    0.36
    এস
    0.36
    POSITIVE LOGITS
    Intermediate
    0.39
    DataType
    0.38
    Elements
    0.38
     Promoter
    0.38
    Fx
    0.37
     shortening
    0.37
     Fuels
    0.37
    Lx
    0.36
    Pattern
    0.36
     Elements
    0.36
    Activations Density 0.009%

    No Known Activations