© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 43697
    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
    to
    0.97
    u
    0.91
    ли
    0.88
    ])));
    0.88
    у
    0.87
    一方
    0.86
    lobby
    0.85
     nour
    0.83
    ю
    0.82
     instill
    0.82
    POSITIVE LOGITS
    チナ
    1.00
     नॉ
    0.94
    IN
    0.93
     draped
    0.90
    ÉR
    0.89
    ecal
    0.88
    óż
    0.88
    OLYBD
    0.88
     traversed
    0.86
    だって
    0.85
    Activations Density 0.003%

    No Known Activations