© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8560
    Prev
    Next
    INDEX
    Explanations

    k-12 and k-5 education levels

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    textarea
    0.52
    window
    0.47
    ญ
    0.46
    LLI
    0.46
     m
    0.45
     man
    0.45
    土
    0.45
     depending
    0.45
     window
    0.45
     dudes
    0.45
    POSITIVE LOGITS
     Tages
    0.55
    dés
    0.51
    ového
    0.51
     Gesundheits
    0.50
    σης
    0.49
     فاذا
    0.49
    érences
    0.49
     perto
    0.47
    ümler
    0.47
    ()*
    0.46
    Activations Density 0.001%

    No Known Activations