© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31880
    Prev
    Next
    INDEX
    Explanations

    paging through documents

    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
     அர்த்த
    0.42
     pages
    0.41
     Pages
    0.40
     filing
    0.38
     প্রতিভা
    0.38
     writing
    0.38
     Scope
    0.38
    页
    0.38
     feline
    0.38
     wiper
    0.37
    POSITIVE LOGITS
     transfusion
    0.41
    Ტ
    0.41
     selectTable
    0.39
    ATIONS
    0.39
     ಪೊಲೀಸ
    0.38
     ಕರಿಬೇವಿನ
    0.37
    સાર
    0.37
     కామె
    0.37
    сім
    0.37
    മു
    0.36
    Activations Density 0.001%

    No Known Activations