© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36253
    Prev
    Next
    INDEX
    Explanations

    professional

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ꯋ
    0.38
     iterator
    0.34
    冫
    0.34
    ٹا
    0.33
    Hrsg
    0.33
    katana
    0.33
     жүктөө
    0.33
     Iterator
    0.33
    juna
    0.33
    畠
    0.32
    POSITIVE LOGITS
     professional
    3.84
    Professional
    3.78
     Professional
    3.77
     профессиона
    3.69
     profesional
    3.67
    professional
    3.56
     profissional
    3.45
     PROFESSIONAL
    3.36
     professionale
    3.30
     profesionales
    3.25
    Activations Density 0.011%

    No Known Activations