© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228351
    Prev
    Next
    INDEX
    Explanations

    require js

    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_6_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
     کی
    1.05
    larını
    0.96
     کتاب
    0.96
    ۔
    0.96
     chega
    0.91
     ?)
    0.91
    จะต้อง
    0.91
     تاکید
    0.91
    های
    0.90
    ların
    0.89
    POSITIVE LOGITS
    ب
    1.48
    ش
    1.19
    م
    1.18
    E
    1.15
    ق
    1.13
    I
    1.09
    ج
    1.09
    را
    1.05
    ين
    1.03
    in
    1.02
    Activations Density 0.000%

    No Known Activations