© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35302
    Prev
    Next
    INDEX
    Explanations

    build(

    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_11_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
    sin
    0.60
     สอน
    0.60
     It
    0.59
     idioms
    0.55
    "—
    0.53
    Normally
    0.51
     There
    0.50
    ?
    0.49
    ($"
    0.49
     primeiros
    0.49
    POSITIVE LOGITS
    ۰۰
    0.61
    fromParams
    0.56
    大脑
    0.56
    ৪৭
    0.54
     ofthe
    0.54
    性感
    0.54
    ed
    0.53
    大佬
    0.53
    ك
    0.52
    وم
    0.51
    Activations Density 0.001%

    No Known Activations