© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136170
    Prev
    Next
    INDEX
    Explanations

    happen to be

    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_12_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
     is
    0.56
    ओ
    0.54
    ARI
    0.53
     happened
    0.50
    ∈
    0.50
    À
    0.48
    ಡಿ
    0.46
    ंजी
    0.46
     kuid
    0.46
    砰
    0.46
    POSITIVE LOGITS
    arbeiter
    0.50
    และการ
    0.49
    ar
    0.47
    an
    0.46
     abstractions
    0.45
    Cantidad
    0.45
     কেবল
    0.44
     ecuaciones
    0.44
     inelastic
    0.44
     ομά
    0.44
    Activations Density 0.000%

    No Known Activations