© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18936
    Prev
    Next
    INDEX
    Explanations

    legumes or bean types

    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_15_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
    皚
    0.61
     داعش
    0.54
    ༄
    0.54
    लट्
    0.53
     전통
    0.53
     유지
    0.52
     (\<
    0.52
     زمین
    0.51
     పరిస్థి
    0.51
     escánd
    0.51
    POSITIVE LOGITS
    r
    0.67
    ing
    0.60
    ,
    0.57
    ox
    0.54
    os
    0.54
    oyer
    0.53
    esor
    0.52
    est
    0.51
    ball
    0.51
    ovor
    0.51
    Activations Density 0.003%

    No Known Activations