© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5223
    Prev
    Next
    INDEX
    Explanations

    Black Lives Matter

    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
     casi
    1.90
    ються
    1.83
    т
    1.80
    ｨ
    1.80
    시키는
    1.77
    瑁
    1.73
    ní
    1.72
     экземпля
    1.72
    кий
    1.71
    nement
    1.70
    POSITIVE LOGITS
    ◍
    2.11
     alkalies
    2.10
    ✹
    2.05
     পক্ষে
    1.99
    ده
    1.97
     vreau
    1.95
     perox
    1.93
     neće
    1.92
     ListTile
    1.90
     spoiling
    1.89
    Activations Density 0.003%

    No Known Activations