© 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. 54287
    Prev
    Next
    INDEX
    Explanations

    develops gluten

    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
    객
    0.40
     전략
    0.38
    ARAJYA
    0.38
     গবেষণ
    0.37
     객
    0.35
     दिक्
    0.35
     molecules
    0.35
     Волго
    0.34
    rieb
    0.34
     справ
    0.34
    POSITIVE LOGITS
     desarroll
    0.42
     Developed
    0.42
     desarrollado
    0.41
     界
    0.40
     sviluppo
    0.39
     развитию
    0.39
     undeveloped
    0.38
    苎
    0.37
     svilupp
    0.37
     entwickeln
    0.37
    Activations Density 0.002%

    No Known Activations