© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8218
    Prev
    Next
    INDEX
    Explanations

    depends heavily on

    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
    
    2.34
    
    2.30
    Twilight
    2.20
    
    2.09
    isRunning
    2.06
    
    2.05
    
    2.04
    ください
    2.02
    dotenv
    1.99
    ിയ
    1.95
    POSITIVE LOGITS
    ″
    2.01
    рить
    1.80
     вот
    1.79
    রে
    1.75
    p
    1.71
    0
    1.68
     crian
    1.63
    ان
    1.61
    при
    1.61
    comer
    1.59
    Activations Density 0.086%

    No Known Activations