© 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
    2. Gemma-3-27B-IT
    3. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87238
    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_23_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
    i
    0.52
     socialism
    0.49
    4
    0.48
    suffix
    0.48
    rumah
    0.47
    setStyleSheet
    0.47
    su
    0.46
    5
    0.46
    bold
    0.46
    sudo
    0.46
    POSITIVE LOGITS
     Di
    0.52
     Aries
    0.50
     Pisces
    0.46
     Prospective
    0.46
    حن
    0.42
     Seasonal
    0.42
     thậm
    0.42
     Qual
    0.41
     complemented
    0.41
     поверну
    0.40
    Activations Density 0.000%

    No Known Activations