© 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. 3405
    Prev
    Next
    INDEX
    Explanations

    interpolation and extrapolation

    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
    ことを
    1.07
     जानकर
    1.00
    टेगरी
    0.94
    frau
    0.92
    ਸ਼ਨ
    0.91
    히
    0.90
    बह
    0.88
    क्यूमेंट
    0.88
    swipe
    0.87
    ﺢ
    0.87
    POSITIVE LOGITS
     deaths
    1.14
    檛
    1.12
    
    0.97
     homicide
    0.96
     fruition
    0.93
     searchValue
    0.91
     appropriated
    0.91
    
    0.91
    ierd
    0.90
    Deaths
    0.90
    Activations Density 0.084%

    No Known Activations