© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26114
    Prev
    Next
    INDEX
    Explanations

    quarks and gluons

    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_10_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
    YC
    0.62
    珐
    0.61
    stArray
    0.60
    </h2>
    0.59
    malar
    0.58
    ফাই
    0.55
    ಜಿ
    0.55
    downs
    0.55
    Mg
    0.54
    ('%
    0.54
    POSITIVE LOGITS
     walkable
    0.59
     storm
    0.54
    ppies
    0.54
     springing
    0.54
    くて
    0.53
     scald
    0.53
     uus
    0.53
     bleed
    0.52
     donning
    0.52
    सेच
    0.51
    Activations Density 0.012%

    No Known Activations