© 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. 4398
    Prev
    Next
    INDEX
    Explanations

    memory and storage capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    يت
    1.05
    นาน
    0.92
     surgiu
    0.90
    $('.
    0.88
    ק
    0.88
    с
    0.88
     parece
    0.85
    ен
    0.84
    то
    0.83
    iyor
    0.82
    POSITIVE LOGITS
    ق
    1.03
     również
    0.79
    底部
    0.75
    ğlu
    0.71
    可视
    0.71
     wheelchairs
    0.67
     nigris
    0.65
    ]\\
    0.65
    ほん
    0.65
    ബ്‌
    0.64
    Activations Density 0.271%

    No Known Activations