© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64752
    Prev
    Next
    INDEX
    Explanations

    specialized and certified professional

    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_41_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
    挈
    0.38
     fint
    0.38
     raincoat
    0.37
    perception
    0.36
     Tow
    0.35
     unfolds
    0.35
    orius
    0.35
    Tow
    0.35
     Rainfall
    0.35
     advances
    0.35
    POSITIVE LOGITS
     Specialized
    0.51
     специали
    0.45
     Specialist
    0.44
     specialized
    0.43
    尃
    0.43
     specialising
    0.42
     specialised
    0.42
    전문
    0.42
     Specialty
    0.41
     specialization
    0.40
    Activations Density 0.009%

    No Known Activations