© 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. 133920
    Prev
    Next
    INDEX
    Explanations

    affordability

    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
    들이
    0.98
    ה
    0.97
     که
    0.94
     שה
    0.90
     Diarsipkan
    0.85
    ۔
    0.83
    
    0.83
    ার্স
    0.82
     Мето
    0.82
    Α
    0.81
    POSITIVE LOGITS
    ле
    1.23
     for
    1.11
    ارة
    0.95
    <0x80>
    0.83
    قي
    0.82
     It
    0.81
     acabó
    0.80
    ี
    0.80
     at
    0.80
    то
    0.79
    Activations Density 0.000%

    No Known Activations