© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226586
    Prev
    Next
    INDEX
    Explanations

    continue straight

    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_10_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
     in
    0.41
    ;
    0.32
    rich
    0.28
    го
    0.27
     V
    0.27
    ir
    0.26
     في
    0.26
    ri
    0.25
    ib
    0.25
    Pa
    0.25
    POSITIVE LOGITS
    م
    0.30
    et
    0.28
    at
    0.28
    스가
    0.27
    がら
    0.26
     китай
    0.25
     BEEN
    0.25
    ায়ণ
    0.24
     negras
    0.24
     semaphore
    0.24
    Activations Density 0.003%

    No Known Activations