© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
    uacute
    1.36
    ˁ
    1.36
    }):=\
    1.35
    ş
    1.30
     tendency
    1.27
    Sau
    1.27
     tempos
    1.23
    cookbook
    1.22
     tienden
    1.20
    ar
    1.20
    POSITIVE LOGITS
    ನಲ್ಲಿ
    1.39
    পূর্ব
    1.38
    दीश
    1.35
     geom
    1.34
    к
    1.33
     ря
    1.33
     стран
    1.30
    शास्त्र
    1.27
    ร
    1.27
    ありません
    1.25
    Activations Density 0.001%

    No Known Activations