© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35814
    Prev
    Next
    INDEX
    Explanations

    cell and cellular processes

    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_11_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
    of
    0.26
     o
    0.25
    که
    0.25
    ง
    0.25
     he
    0.25
    Tại
    0.25
    ۶
    0.24
    י
    0.24
     của
    0.24
    ของ
    0.23
    POSITIVE LOGITS
    ;",
    0.26
    ὸ
    0.24
     UPC
    0.22
     geotechnical
    0.21
    rinsim
    0.21
    ();//
    0.21
    ;"+
    0.21
     contin
    0.20
     APC
    0.20
    OHC
    0.20
    Activations Density 0.010%

    No Known Activations