© 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. 5918
    Prev
    Next
    INDEX
    Explanations

    class or def followed by identifier

    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
    Scaled
    0.89
    panic
    0.88
    ület
    0.84
    なり
    0.83
     majoring
    0.83
     ơn
    0.81
    ч
    0.80
               
    0.78
    (−
    0.74
    .\
    0.74
    POSITIVE LOGITS
    amı
    0.89
    mathscr
    0.87
     lepton
    0.86
    ী
    0.86
     bilo
    0.85
    ंमुळे
    0.85
    كية
    0.84
    ০০
    0.84
    ные
    0.84
     Februar
    0.84
    Activations Density 0.019%

    No Known Activations