© 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. 5927
    Prev
    Next
    INDEX
    Explanations

    polysaccharides, polymorphism, ethylene, methyl

    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
    부터
    2.48
    ות
    2.42
     pancreas
    2.27
    beat
    2.26
    idão
    2.16
    [
    2.14
    パクト
    2.14
    ें
    2.12
    شنا
    2.12
     Akademie
    2.10
    POSITIVE LOGITS
    he
    2.27
     tratti
    1.96
    at
    1.92
    ll
    1.86
    ಾ
    1.84
    บาล
    1.83
    we
    1.82
     नै
    1.81
    一丝
    1.81
     grave
    1.80
    Activations Density 0.022%

    No Known Activations