© 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-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260500
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    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
    मिट
    0.14
    nimi
    0.13
    ynyt
    0.13
    ழ்பெற்ற
    0.13
    feder
    0.13
     한
    0.13
    testid
    0.13
     inégal
    0.13
    מת
    0.13
     Đế
    0.13
    POSITIVE LOGITS
     мя
    0.13
     прият
    0.13
    🚢
    0.13
     Sampson
    0.13
     into
    0.12
    iesen
    0.12
     Mab
    0.12
     cyber
    0.12
     ниже
    0.12
     கிழ
    0.12
    Activations Density 0.003%

    No Known Activations