© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6494
    Prev
    Next
    INDEX
    Explanations

    file upload

    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
     नमक
    0.39
     cyclase
    0.39
    𒌨
    0.38
    SwingConstants
    0.38
    ObjectUnderTest
    0.38
    ম্ম
    0.37
    ArgsEnv
    0.37
    紅茶
    0.36
    =@@
    0.35
    ΙΚ
    0.35
    POSITIVE LOGITS
     upload
    0.76
     file
    0.73
     Upload
    0.73
    upload
    0.71
    File
    0.68
     uploads
    0.67
     File
    0.67
    FILE
    0.66
     streaming
    0.66
    file
    0.64
    Activations Density 0.180%

    No Known Activations