© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19815
    Prev
    Next
    INDEX
    Explanations

    phrases and grammar improvements

    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_15_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
     виду
    0.27
     dreamstime
    0.26
     σημαν
    0.26
     candid
    0.25
     suss
    0.25
     diciamo
    0.25
     knn
    0.24
     την
    0.24
     candidacy
    0.24
    𝗳
    0.24
    POSITIVE LOGITS
    ро
    0.25
    ар
    0.23
    keits
    0.22
    क्रम
    0.21
    reason
    0.21
    زام
    0.21
     Soldaten
    0.21
    هار
    0.21
    --");
    0.21
     Wro
    0.20
    Activations Density 0.059%

    No Known Activations