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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3685
    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
    هن
    1.81
    Procedure
    1.60
    為了
    1.60
    Biography
    1.50
    jia
    1.50
     लिए
    1.47
    Subtraction
    1.43
    f
    1.41
     przykład
    1.41
    ט
    1.41
    POSITIVE LOGITS
    al
    2.29
     Wynne
    1.88
    alık
    1.78
    новништво
    1.76
     outcomes
    1.75
    요
    1.66
    mehr
    1.63
     lawns
    1.63
     shelving
    1.62
     introns
    1.60
    Activations Density 0.000%

    No Known Activations