© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5923
    Prev
    Next
    INDEX
    Explanations

    ipv4 vs. ipv6

    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
    ا
    4.60
     dioxane
    3.79
     quadrants
    3.17
    ঠা
    3.03
    不像
    3.02
     curbing
    3.00
    рь
    2.99
    ty
    2.92
    این
    2.92
     avendo
    2.87
    POSITIVE LOGITS
     translateY
    3.83
    ن
    3.72
    ৯
    3.43
    нің
    3.40
    ли
    3.32
    selves
    3.27
    Просе
    3.25
    কেন্ড
    3.24
    न
    3.12
    ৯০
    3.10
    Activations Density 0.077%

    No Known Activations