Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4252
    Prev
    Next
    INDEX
    Explanations

    over the network or time

    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
    jogador
    1.21
    ZIONE
    1.06
    ش
    1.04
     жизни
    1.04
    mais
    0.99
    arctic
    0.95
    pping
    0.93
     علمی
    0.93
    époque
    0.92
    ва
    0.91
    POSITIVE LOGITS
     behalf
    1.61
     Highness
    1.22
     headphones
    1.16
    
    1.16
     persuaded
    1.16
     translateY
    1.12
     summarised
    1.09
    MainWindow
    1.08
    breviations
    1.08
     headsets
    1.06
    Activations Density 0.077%

    No Known Activations