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. 4460
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    嵋
    1.05
    secrets
    1.04
    IVITY
    1.03
    
    1.02
     estilos
    0.98
     gesamte
    0.97
     wallpapers
    0.96
    ající
    0.96
    तों
    0.93
     kirj
    0.92
    POSITIVE LOGITS
    tired
    0.99
    erweise
    0.97
     unbeatable
    0.93
    ل
    0.93
    ফোন
    0.93
     Ephesians
    0.91
     rationally
    0.91
     बाढ़
    0.91
    这时候
    0.89
    డుగు
    0.89
    Activations Density 0.104%

    No Known Activations