© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99774
    Prev
    Next
    INDEX
    Explanations

    top lane

    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_14_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
    U
    0.16
    [
    0.16
    ree
    0.15
    γ
    0.15
    ry
    0.15
    4
    0.15
    na
    0.15
    3
    0.15
    Y
    0.15
    X
    0.14
    POSITIVE LOGITS
     Strickland
    0.18
     Bruck
    0.16
     Siri
    0.16
     Museums
    0.16
     Steck
    0.16
     revisar
    0.16
     Streak
    0.16
     Liverpool
    0.16
     sır
    0.15
     nicknamed
    0.15
    Activations Density 0.002%

    No Known Activations