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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3621
    Prev
    Next
    INDEX
    Explanations

    Inca Empire, Machu Picchu, citadel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ע
    0.57
    g
    0.53
    ial
    0.53
    fam
    0.52
    情况
    0.51
    ()=>{
    0.51
    wanie
    0.48
    WAN
    0.47
    Dentro
    0.47
    鹑
    0.47
    POSITIVE LOGITS
    ли
    0.71
     warriors
    0.60
    
    0.59
    
    0.56
     costumes
    0.55
    ᐉ
    0.55
     examiners
    0.54
     voyages
    0.54
     boomers
    0.54
     painkillers
    0.52
    Activations Density 0.004%

    No Known Activations