© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4941
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by century

    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_3_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
    en
    0.97
    ни
    0.87
    el
    0.80
    м
    0.71
    ARAJYA
    0.68
    ynh
    0.66
    ുടെ
    0.66
     Utara
    0.66
     arsenic
    0.65
    ع
    0.65
    POSITIVE LOGITS
    また
    0.75
    𝐥
    0.74
    𝐢
    0.69
     మంది
    0.67
    𝐡
    0.67
    𝐛
    0.65
    ంటి
    0.65
    г
    0.62
     walled
    0.61
    ()=>{
    0.60
    Activations Density 0.028%

    No Known Activations