© 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-16K
    7. 3696
    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_16k_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
     haue
    1.34
     archipelago
    1.20
     Sono
    1.16
     경우에는
    1.16
    ো
    1.12
    ものである
    1.09
    চয়
    1.06
    ické
    1.05
     Следу
    1.05
    繁忙時間服務
    1.05
    POSITIVE LOGITS
    t
    1.05
    aving
    0.92
    eo
    0.91
    ector
    0.90
    tig
    0.90
    g
    0.90
    ட்
    0.89
     bila
    0.88
    ką
    0.88
     fortement
    0.87
    Activations Density 1.482%

    No Known Activations