© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    watching videos, concerts, or events

    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
    
    0.56
     permitir
    0.53
    
    0.52
    oğlu
    0.50
    𝒈
    0.49
     أح
    0.49
    ipheral
    0.49
     poter
    0.49
     differ
    0.48
    ங்கிணை
    0.48
    POSITIVE LOGITS
    ng
    0.53
    ЛЕ
    0.53
    主义
    0.52
    ttl
    0.52
    ман
    0.52
     смотре
    0.51
    मात्र
    0.50
     milyon
    0.50
     savag
    0.49
    🍿
    0.49
    Activations Density 0.287%

    No Known Activations