© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32124
    Prev
    Next
    INDEX
    Explanations

    hours

    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_31_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
     Aloha
    0.34
     customized
    0.31
     customize
    0.30
     इफ
    0.30
     customizable
    0.30
    赁
    0.29
     Tell
    0.29
     Ме
    0.29
     ܐ
    0.29
     Customize
    0.29
    POSITIVE LOGITS
     ಸಂಖ್ಯ
    0.29
     되겠
    0.28
     khắc
    0.27
    ici
    0.27
    ۴
    0.27
    ependent
    0.27
    azem
    0.26
    enca
    0.26
     Taschen
    0.26
    isan
    0.26
    Activations Density 0.002%

    No Known Activations