© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 30738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    ان
    1.09
    न
    1.01
    ن
    0.94
    ت
    0.93
    ر
    0.90
    م
    0.90
    يد
    0.89
    ید
    0.88
    ম
    0.88
    нні
    0.83
    POSITIVE LOGITS
     terem
    0.89
     Oat
    0.84
     tiveram
    0.79
     HMO
    0.78
    steroidal
    0.78
    ened
    0.77
     destinados
    0.75
    zeit
    0.74
    íssimo
    0.74
    ÉRI
    0.73
    Activations Density 0.000%

    No Known Activations