© 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. 15200
    Prev
    Next
    INDEX
    Explanations

    rule of thumb

    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
    ly
    0.47
     dioc
    0.46
    हिता
    0.45
     покупки
    0.45
     forested
    0.43
    ėjo
    0.43
    鯱
    0.43
    は大
    0.43
    ates
    0.43
    ☓
    0.43
    POSITIVE LOGITS
    ক
    0.64
    ק
    0.60
    衰
    0.53
    Sí
    0.51
     Sí
    0.50
    तत्
    0.49
    o
    0.49
    기
    0.49
    షల్
    0.48
    ร
    0.48
    Activations Density 0.000%

    No Known Activations