Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4088
    Prev
    Next
    INDEX
    Explanations

    cultural heritage and trends

    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
    ر
    0.79
    ки
    0.71
    بت
    0.71
    ات
    0.68
    形の
    0.67
     हटाने
    0.67
     supuesto
    0.66
    മാർ
    0.66
    ꜰ
    0.65
    ট
    0.65
    POSITIVE LOGITS
     Bhojpuri
    0.73
    ../../
    0.72
    ../../../
    0.70
    특별시
    0.68
    UW
    0.68
    รง
    0.67
    মন
    0.67
    mpeg
    0.66
     والوں
    0.66
     wcześniej
    0.65
    Activations Density 0.135%

    No Known Activations