© 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. 24-GEMMASCOPE-2-RES-262K
    7. 4136
    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_24_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
    ه
    0.82
     жа
    0.76
    車の
    0.70
    車
    0.70
    대한
    0.66
     تد
    0.65
     ""){
    0.65
     cortos
    0.64
     ي
    0.63
    즐
    0.63
    POSITIVE LOGITS
     amphibians
    0.80
     kadın
    0.77
     lanthan
    0.76
     aptly
    0.75
     freshwater
    0.75
     strontium
    0.75
     recessive
    0.74
     secretive
    0.74
     scientists
    0.74
     diamonds
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.