© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37571
    Prev
    Next
    INDEX
    Explanations

    "Please note that"

    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
    手
    0.94
    ул
    0.84
    п
    0.80
    ل
    0.77
    ל
    0.77
    تك
    0.76
    تن
    0.75
    تون
    0.75
    تر
    0.72
    تو
    0.72
    POSITIVE LOGITS
    o
    1.19
    a
    1.13
    0
    0.73
     integrante
    0.69
    rin
    0.63
    eer
    0.61
     interact
    0.61
    oop
    0.60
    া
    0.59
    que
    0.59
    Activations Density 0.002%

    No Known Activations