© 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. 2470
    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
    D
    0.91
    L
    0.90
    R
    0.88
    J
    0.85
     arxiv
    0.83
    M
    0.80
    P
    0.80
    LGBT
    0.80
     이를
    0.79
    W
    0.79
    POSITIVE LOGITS
     characterizes
    1.15
     characteristics
    1.14
     regulates
    1.08
     fasteners
    1.02
    がたくさん
    1.02
     substances
    1.00
     determines
    0.99
     establishes
    0.98
     organisms
    0.97
     emberek
    0.97
    Activations Density 3.771%

    No Known Activations