© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74666
    Prev
    Next
    INDEX
    Explanations

    American expansion and ideals

    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_31_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
    [,]
    0.36
    Office
    0.35
    Fonts
    0.35
    Package
    0.35
    FirstName
    0.35
    Hyper
    0.34
    antro
    0.34
    قار
    0.33
     বস্ত্র
    0.33
     сражение
    0.33
    POSITIVE LOGITS
     yù
    0.41
     escolares
    0.39
     industriale
    0.39
     economia
    0.38
    镰
    0.38
     riserv
    0.38
     economica
    0.37
     industriales
    0.37
     escolas
    0.37
    lastKey
    0.36
    Activations Density 0.028%

    No Known Activations