© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9751
    Prev
    Next
    INDEX
    Explanations

    structured information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     Sam
    0.64
     Republican
    0.64
     ഫ
    0.63
    Republic
    0.62
    bitflag
    0.62
    shu
    0.60
    ặc
    0.60
     Four
    0.60
    NgramModel
    0.60
     Wild
    0.60
    POSITIVE LOGITS
    卞
    0.71
     Mx
    0.67
     மாத
    0.67
     rising
    0.66
    rising
    0.65
    وال
    0.64
     वर्षा
    0.64
     admitting
    0.64
    inius
    0.64
     izvr
    0.63
    Activations Density 0.333%

    No Known Activations