© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37647
    Prev
    Next
    INDEX
    Explanations

    something is key

    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_11_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
    ವಾದ
    0.57
    িট
    0.54
    airement
    0.53
     plupart
    0.52
    hesized
    0.52
    ༢
    0.50
    ުގައި
    0.50
    த்தில்
    0.50
     बदलकर
    0.50
    翕
    0.50
    POSITIVE LOGITS
     u
    0.63
     H
    0.60
     education
    0.60
     Europeans
    0.60
     cockroaches
    0.59
     Extension
    0.59
     imperialism
    0.58
     brownies
    0.58
     creases
    0.57
     extension
    0.57
    Activations Density 0.008%

    No Known Activations