© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99950
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
    B
    0.61
    ه
    0.54
    ائع
    0.52
    นอก
    0.52
    ව
    0.50
    M
    0.49
    3
    0.49
    ва
    0.48
     Vend
    0.48
     proš
    0.48
    POSITIVE LOGITS
    स्ट्र
    0.42
     συνο
    0.41
    ;?>
    0.40
    ασίας
    0.40
     accusing
    0.40
     roommates
    0.39
     antibodies
    0.39
     devastating
    0.38
     woes
    0.38
    rus
    0.38
    Activations Density 0.000%

    No Known Activations