© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3359
    Prev
    Next
    INDEX
    Explanations

    links and programming sites

    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
    ა
    0.66
    ভাবে
    0.62
    嘧
    0.61
     morrer
    0.56
    ोग
    0.55
    ت
    0.55
     vozila
    0.55
    અ
    0.54
     principais
    0.54
     vasomotor
    0.54
    POSITIVE LOGITS
    le
    0.66
    liği
    0.58
    yi
    0.55
    zaw
    0.54
     ноги
    0.54
    "{
    0.53
    z
    0.53
     plurality
    0.51
    তৃত
    0.51
    NSInteger
    0.50
    Activations Density 0.141%

    No Known Activations