© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198048
    Prev
    Next
    INDEX
    Explanations

    connecting to concepts

    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_12_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
    У
    0.57
     ineffective
    0.52
    EL
    0.50
    U
    0.50
    ای
    0.50
    М
    0.49
    ם
    0.48
    los
    0.47
     grapes
    0.47
    К
    0.46
    POSITIVE LOGITS
     관광
    0.60
    ia
    0.59
     attham
    0.58
     puriso
    0.56
     адам
    0.56
    اضره
    0.55
     சிலர்
    0.55
     туристов
    0.55
     четы
    0.54
     kammam
    0.53
    Activations Density 0.001%

    No Known Activations