© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193509
    Prev
    Next
    INDEX
    Explanations

    processing text prompts

    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_9_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
    ig
    0.71
    is
    0.66
    ad
    0.61
    a
    0.60
    it
    0.59
     Ripp
    0.58
    are
    0.56
    ass
    0.56
    ha
    0.55
    to
    0.55
    POSITIVE LOGITS
    ني
    0.52
     سنج
    0.51
    кона
    0.50
    чиго
    0.49
    Santiago
    0.47
    гун
    0.45
     ૨
    0.45
    ને
    0.45
    గు
    0.45
     Santiago
    0.45
    Activations Density 0.001%

    No Known Activations