© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58749
    Prev
    Next
    INDEX
    Explanations

    now

    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
    ál
    0.62
    -
    0.59
    ya
    0.58
     mathvariant
    0.57
     medalist
    0.57
    /
    0.56
     Cloud
    0.55
    ла
    0.55
    ர்
    0.55
     WJ
    0.55
    POSITIVE LOGITS
    I
    0.75
    빨
    0.60
    S
    0.58
    defence
    0.55
    ‌కు
    0.55
     말미암아
    0.55
    Мы
    0.55
    取る
    0.54
    ()=>{
    0.54
    Afrique
    0.54
    Activations Density 0.005%

    No Known Activations