© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41065
    Prev
    Next
    INDEX
    Explanations

    Sarandë, Ksamil, Sarnen, SARN, Sarrus

    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_3_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
     esclusivamente
    0.77
    م
    0.77
     éventuellement
    0.75
    ために
    0.75
    R
    0.75
     enthous
    0.73
     meticul
    0.72
     exclusivamente
    0.72
     dovrà
    0.72
    ように
    0.71
    POSITIVE LOGITS
    ة
    1.09
    k
    0.82
    ak
    0.78
    اد
    0.75
    ీ
    0.73
    ัง
    0.72
    ing
    0.71
    ate
    0.71
    ong
    0.70
    ana
    0.70
    Activations Density 0.003%

    No Known Activations