© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    'Content-Type' headers

    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
    𝑢
    2.00
    𝑣
    1.99
    𝑛
    1.98
    𝑇
    1.97
     रूप
    1.94
     mediaPlayer
    1.94
    ئی
    1.93
    𝑐
    1.88
     instalments
    1.86
    𝑘
    1.85
    POSITIVE LOGITS
    t
    2.39
    d
    2.29
    ್‌
    2.22
    wości
    2.06
    time
    1.95
    {},
    1.93
    т
    1.89
    ところに
    1.88
    antera
    1.87
    ının
    1.86
    Activations Density 0.001%

    No Known Activations