© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6898
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    品种
    0.46
    を有する
    0.45
     reconocida
    0.43
    誢
    0.42
    ()=>{
    0.42
     permitem
    0.41
     ਹੈ
    0.41
    <unused335>
    0.40
     podría
    0.40
    訸
    0.40
    POSITIVE LOGITS
    k
    0.61
    i
    0.57
    ت
    0.54
    ف
    0.48
    ed
    0.46
     and
    0.45
    ي
    0.44
    م
    0.43
    de
    0.43
    o
    0.42
    Activations Density 2.324%

    No Known Activations