© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    docker run flags like `-d` or `-it`

    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
     Exercise
    0.38
     Р
    0.38
     orthodoxy
    0.37
     الر
    0.37
     watermelon
    0.36
    EXCLUSIVE
    0.36
    М
    0.36
    █
    0.36
     মজুদ
    0.35
    submarine
    0.35
    POSITIVE LOGITS
    आईटी
    0.40
    ंटे
    0.38
    gt
    0.37
     demonstrate
    0.37
     Demonstrate
    0.37
     GT
    0.37
     zit
    0.37
    ttamente
    0.37
    dep
    0.37
     الكتاب
    0.36
    Activations Density 0.002%

    No Known Activations