© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49667
    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
    জমেন্ট
    0.33
    erving
    0.33
    Miner
    0.33
     Miner
    0.33
    buck
    0.32
    竑
    0.32
     sian
    0.32
    贝尔
    0.32
    蓴
    0.31
    别
    0.31
    POSITIVE LOGITS
     Diabetes
    0.42
     clinique
    0.42
     Infants
    0.42
     clinically
    0.42
     někter
    0.41
     பாதிக்கப்பட்ட
    0.41
     Physician
    0.40
     progesterone
    0.40
    ായ്
    0.40
     PCOS
    0.40
    Activations Density 0.000%

    No Known Activations