© 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. 4831
    Prev
    Next
    INDEX
    Explanations

    throw new TypeError / Error

    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
     dotyczą
    0.82
    
    0.76
     précie
    0.70
     звер
    0.69
    を表示
    0.69
     velha
    0.69
    Р
    0.68
     آیا
    0.68
     Descent
    0.68
    ical
    0.68
    POSITIVE LOGITS
    ভাবে
    0.89
    仡
    0.81
     potentially
    0.80
     randomIndex
    0.78
    деги
    0.78
     linewidth
    0.78
    topLeft
    0.77
     slight
    0.76
    िंग
    0.76
    igned
    0.75
    Activations Density 0.007%

    No Known Activations