© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4787
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and machine learning

    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_3_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
    هي
    1.74
     constat
    1.55
    ebay
    1.53
    ön
    1.53
    ी
    1.51
    ])
    1.45
     karet
    1.43
     harm
    1.42
    e
    1.39
    ে
    1.39
    POSITIVE LOGITS
    و
    1.76
    uous
    1.59
     पुराण
    1.47
     ointment
    1.45
    р
    1.45
    пе
    1.44
    
    1.43
    eniya
    1.43
     legions
    1.43
    ю
    1.43
    Activations Density 0.563%

    No Known Activations