© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8637
    Prev
    Next
    INDEX
    Explanations

    back injuries or pain

    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_13_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
     senador
    0.50
    Ｇ
    0.45
     vocês
    0.43
     această
    0.42
     oriente
    0.42
     métodos
    0.41
     ObjectID
    0.40
     Companies
    0.40
     também
    0.40
     умира
    0.40
    POSITIVE LOGITS
    quard
    0.44
    J
    0.43
     स्वर्ण
    0.42
    碚
    0.41
    QCD
    0.40
    명의
    0.40
    ajada
    0.40
    Neck
    0.39
    presentableId
    0.39
    jacke
    0.39
    Activations Density 0.030%

    No Known Activations