© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102042
    Prev
    Next
    INDEX
    Explanations

    keep informed

    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_16_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
     kinks
    0.52
     begs
    0.51
    AssetsRequest
    0.50
     asks
    0.49
     طلب
    0.49
    ي
    0.48
     كان
    0.48
    𝙍
    0.47
     كي
    0.47
    จากการ
    0.47
    POSITIVE LOGITS
     Potatoes
    0.55
     国産
    0.53
     Motor
    0.52
     Roasted
    0.51
     Baseball
    0.51
     Desert
    0.50
     Vegetable
    0.50
     Beautiful
    0.49
    啭
    0.49
    சிக்கும்
    0.48
    Activations Density 0.003%

    No Known Activations