© 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. 37609
    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
     отдельных
    0.96
     коюм
    0.83
    isering
    0.82
     refundable
    0.81
    𝟎
    0.76
    matically
    0.75
     разговари
    0.74
     rodz
    0.73
    უალ
    0.73
     долла
    0.73
    POSITIVE LOGITS
    ن
    1.15
    न
    0.96
    स
    0.88
    ン
    0.86
    傛
    0.82
    ச
    0.82
    메
    0.80
    نیا
    0.79
    ड
    0.77
    Roasted
    0.74
    Activations Density 0.000%

    No Known Activations