© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35092
    Prev
    Next
    INDEX
    Explanations

    follow instructions

    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_11_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
     discret
    0.64
    됩
    0.57
     stát
    0.55
    ిత
    0.54
    如果在
    0.54
     verrou
    0.54
     organiza
    0.53
     antagon
    0.53
     vacances
    0.53
    ة
    0.53
    POSITIVE LOGITS
    pt
    0.65
    GOOD
    0.64
    kt
    0.63
    Units
    0.63
    ONE
    0.63
    riters
    0.61
    THERS
    0.59
    WS
    0.59
     Hasil
    0.59
    MyToolkit
    0.59
    Activations Density 0.003%

    No Known Activations