© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205965
    Prev
    Next
    INDEX
    Explanations

    prime number computations

    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_20_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
     improve
    0.48
     mango
    0.48
     cult
    0.47
     blessing
    0.47
     M
    0.47
     improves
    0.47
     improving
    0.46
     Stim
    0.46
     joined
    0.46
     Role
    0.46
    POSITIVE LOGITS
    CrL
    0.44
     ಅಭಿಮಾನ
    0.43
    utzt
    0.42
    投标人
    0.42
    UGUST
    0.42
    athletes
    0.42
    луйста
    0.40
    $.;
    0.40
    分手
    0.40
     Worte
    0.40
    Activations Density 0.003%

    No Known Activations