© 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. 5898
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and code symbols

    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
    erry
    0.57
    )}=
    0.57
    发展的
    0.53
    \,.
    0.53
    utable
    0.52
    n
    0.51
    
    0.51
     tricked
    0.50
    党员
    0.48
    ٪
    0.48
    POSITIVE LOGITS
    ي
    0.75
     tiszt
    0.65
    闶
    0.58
     gewähr
    0.55
    ク
    0.55
    repe
    0.54
    阌
    0.52
     vouloir
    0.52
    教育部
    0.52
     postice
    0.52
    Activations Density 0.066%

    No Known Activations