© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181385
    Prev
    Next
    INDEX
    Explanations

    two teams or nations

    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_24_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
    pertension
    0.41
    วัสดี
    0.38
    颓
    0.38
     dynamism
    0.38
    izontally
    0.37
    ximity
    0.36
     kèo
    0.35
    いただけます
    0.34
    Optim
    0.34
    頹
    0.34
    POSITIVE LOGITS
     début
    0.44
     Beginner
    0.41
     prelim
    0.41
     Eph
    0.39
     BEGIN
    0.38
     pru
    0.38
    voor
    0.38
    cattle
    0.38
    初步
    0.38
    debut
    0.38
    Activations Density 0.000%

    No Known Activations