© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37820
    Prev
    Next
    INDEX
    Explanations

    Practical nurse professions

    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
    ’
    0.87
    5
    0.76
    पूर्वी
    0.71
    five
    0.68
    0
    0.61
    ５
    0.61
    6
    0.60
    ۵
    0.60
    8
    0.59
    reading
    0.59
    POSITIVE LOGITS
     motionProxy
    0.59
     ውሃ
    0.58
     chats
    0.56
     intestate
    0.55
     INSEE
    0.54
     VIA
    0.53
     hostels
    0.52
     IA
    0.51
     Shayari
    0.50
     index
    0.50
    Activations Density 0.000%

    No Known Activations