© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259373
    Prev
    Next
    INDEX
    Explanations

    political and social polarization

    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_10_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
     adicionales
    0.71
     pliable
    0.69
     സെക്രട്ട
    0.69
     cargoes
    0.67
    商品は
    0.67
    
    0.67
     leng
    0.67
    
    0.66
     suficiente
    0.66
    とめ
    0.65
    POSITIVE LOGITS
     comparing
    0.68
     called
    0.67
     estranged
    0.67
    द्दीन
    0.64
     using
    0.64
     allergy
    0.61
     computer
    0.60
     beloved
    0.59
     reconciling
    0.59
    師
    0.58
    Activations Density 0.002%

    No Known Activations