© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219198
    Prev
    Next
    INDEX
    Explanations

    describe topic

    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_16_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
    S
    0.67
    o
    0.64
    ↵
    0.60
    in
    0.53
    l
    0.52
     and
    0.50
    C
    0.48
    io
    0.47
    at
    0.47
    an
    0.47
    POSITIVE LOGITS
     পেই
    0.58
     Австра
    0.56
     nameWithOwner
    0.55
    havior
    0.52
     estarán
    0.52
     IncludeField
    0.52
     ©️
    0.52
     Ян
    0.50
     मुल
    0.50
     inéd
    0.49
    Activations Density 0.000%

    No Known Activations