© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     então
    0.41
    zus
    0.38
     Wilkins
    0.37
    }+(
    0.37
     स्वातंत्र्य
    0.37
     Square
    0.36
    िटेशन
    0.36
     là
    0.36
    ihan
    0.35
     uneven
    0.35
    POSITIVE LOGITS
    消费
    0.43
     větš
    0.37
    consumer
    0.36
     G
    0.36
     GIS
    0.36
     contener
    0.35
     having
    0.35
     의견
    0.35
     pouvant
    0.34
    识别
    0.34
    Activations Density 0.000%

    No Known Activations