© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102589
    Prev
    Next
    INDEX
    Explanations

    name, element, Accompany, Fermentation, Century, Burundi, all

    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_14_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
     Brewing
    0.53
     missionary
    0.52
     क्रांतिकारी
    0.50
     innovating
    0.50
     तीन
    0.49
     revolutionaries
    0.49
    ﻈ
    0.49
     використання
    0.48
    t
    0.48
    ﻄ
    0.48
    POSITIVE LOGITS
    kül
    0.52
    áver
    0.52
    㤟
    0.51
    fetched
    0.49
    韆
    0.49
    >',
    0.48
    uose
    0.48
    粓
    0.47
    </b>
    0.47
     variación
    0.47
    Activations Density 0.000%

    No Known Activations