© 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. 4997
    Prev
    Next
    INDEX
    Explanations

    detectMultiScale

    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
    प
    1.91
     siapa
    1.82
    ن
    1.79
     زمانی
    1.78
    за
    1.73
    ైన
    1.70
     Semua
    1.61
    ار
    1.59
    قال
    1.59
    стро
    1.59
    POSITIVE LOGITS
    adays
    1.88
    ת
    1.84
     Перейти
    1.66
    Ро
    1.62
    মতী
    1.59
    م
    1.57
    "#
    1.52
    ILAR
    1.52
    "_
    1.51
    :])
    1.50
    Activations Density 0.002%

    No Known Activations