© 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. 3107
    Prev
    Next
    INDEX
    Explanations

    military convoy, order, operations, action

    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
    tos
    0.99
    ০০
    0.96
    onnay
    0.92
    ח
    0.92
    ‌های
    0.91
    cian
    0.87
    et
    0.87
    ころ
    0.87
    má
    0.84
     দায়ের
    0.84
    POSITIVE LOGITS
     verwend
    0.82
     soldiers
    0.81
    
    0.81
    
    0.80
    ści
    0.78
     convent
    0.76
     dira
    0.76
    vec
    0.76
    ত্রী
    0.74
    を有
    0.74
    Activations Density 0.074%

    No Known Activations