© 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. 413
    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
     HashTable
    0.79
    ა
    0.78
    ى
    0.75
     писатель
    0.74
     здоровье
    0.73
     обеспечение
    0.73
     экономического
    0.71
     поведения
    0.71
     그럼
    0.69
    럴
    0.69
    POSITIVE LOGITS
    に
    0.84
     regretted
    0.79
    Де
    0.76
    ई
    0.74
    М
    0.73
    にい
    0.73
    砼
    0.72
    ंझ
    0.72
    𝐄
    0.71
    𝗘
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.