© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88401
    Prev
    Next
    INDEX
    Explanations

    a response containing "Answer"

    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_18_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
     społ
    0.50
     genera
    0.49
     mức
    0.49
     گرو
    0.49
     raised
    0.49
     jiwa
    0.49
    с
    0.49
     khẩu
    0.48
    스
    0.48
     şekilde
    0.47
    POSITIVE LOGITS
     Está
    0.53
     Estoy
    0.50
     Dress
    0.49
     acht
    0.48
     V
    0.48
    ริ่ม
    0.47
     endast
    0.46
     Estou
    0.46
     Danke
    0.46
     neue
    0.46
    Activations Density 0.005%

    No Known Activations