© 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-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9662
    Prev
    Next
    INDEX
    Explanations

    Arabic phrases and terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     মহারাজ
    0.75
     cumpl
    0.70
    ҷ
    0.67
     సీ
    0.67
     அளவிற்கு
    0.67
     tien
    0.67
    cnica
    0.66
     théâtre
    0.66
    ម្រ
    0.66
    璺
    0.65
    POSITIVE LOGITS
    ood
    0.81
     നമ
    0.77
    hatu
    0.75
     dispersive
    0.66
    রের
    0.65
    าก
    0.65
    reen
    0.65
    ूर
    0.65
     Cruises
    0.63
     Liner
    0.63
    Activations Density 0.022%

    No Known Activations