© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39890
    Prev
    Next
    INDEX
    Explanations

    empresa

    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_3_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
    in
    1.05
    ي
    0.98
    i
    0.96
    ת
    0.95
    at
    0.94
    0.89
    ت
    0.87
    D
    0.86
    يي
    0.84
    O
    0.84
    POSITIVE LOGITS
    सी
    0.84
    ます
    0.71
    扡
    0.70
    م
    0.66
    ンの
    0.64
    㞓
    0.64
    ется
    0.64
     دوسرا
    0.64
     capazes
    0.63
    포
    0.63
    Activations Density 0.001%

    No Known Activations