© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    say, word, from

    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
    ਤੇ
    2.04
     oysters
    2.04
    ﻲ
    2.03
     최
    1.95
    沅
    1.95
     оди
    1.94
     इसमें
    1.93
    ᱸ
    1.93
     остальных
    1.92
    ﺴ
    1.92
    POSITIVE LOGITS
     propria
    1.72
    lə
    1.71
    씀
    1.70
     terb
    1.70
     tandem
    1.66
    ranno
    1.65
    Executable
    1.65
    当て
    1.63
     médical
    1.62
    흙
    1.62
    Activations Density 0.020%

    No Known Activations