© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3023
    Prev
    Next
    INDEX
    Explanations

    trade wars, tensions, deals, agreements

    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_5_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
    sized
    1.72
    ли
    1.69
    в
    1.64
    તર
    1.59
    kafka
    1.55
    sizing
    1.55
    人心
    1.55
    år
    1.53
     prest
    1.51
    ities
    1.48
    POSITIVE LOGITS
     poche
    1.82
    雎
    1.81
     تصوی
    1.80
     novedades
    1.79
    <unused48>
    1.77
     inici
    1.75
     enemies
    1.73
     acuerdos
    1.72
    এবার
    1.71
    淞
    1.69
    Activations Density 0.011%

    No Known Activations