© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96238
    Prev
    Next
    INDEX
    Explanations

    for a while now

    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
    Negative Logits
     remedies
    0.40
    ip
    0.38
    uks
    0.38
    kers
    0.37
    ises
    0.37
    u
    0.37
    ira
    0.36
    igo
    0.36
    ucs
    0.35
     avalanche
    0.35
    POSITIVE LOGITS
     до
    0.36
     Sekarang
    0.35
    𝟖
    0.35
    рьох
    0.34
     찍
    0.34
     mình
    0.34
     Learned
    0.34
     بين
    0.33
    Schw
    0.33
     своїх
    0.33
    Activations Density 0.001%

    No Known Activations