© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57888
    Prev
    Next
    INDEX
    Explanations

    art of

    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_11_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
    '
    0.86
    ’
    0.65
    '][
    0.61
     deactivate
    0.58
     hindering
    0.57
    st
    0.55
    sej
    0.54
     associa
    0.54
     ejac
    0.54
    ft
    0.53
    POSITIVE LOGITS
    า
    0.58
    িয়েত
    0.56
    ตำ
    0.54
    ração
    0.54
    ിയാണ്
    0.53
     ነው።
    0.52
    Cement
    0.52
    การ
    0.52
    ъл
    0.52
    Catagory
    0.52
    Activations Density 0.005%

    No Known Activations