© 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. 39016
    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
    icción
    0.76
    FLICT
    0.75
    ’
    0.73
    ename
    0.67
    achella
    0.67
    א
    0.66
     illetve
    0.64
    ámenes
    0.64
    1
    0.64
    ì
    0.64
    POSITIVE LOGITS
     rules
    0.79
     when
    0.76
     বিষয়ে
    0.75
     basics
    0.75
     processes
    0.74
     structures
    0.73
     தருக
    0.73
     tasks
    0.72
     når
    0.72
     জন্য
    0.72
    Activations Density 0.444%

    No Known Activations