© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62681
    Prev
    Next
    INDEX
    Explanations

    objects of a specific size

    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_11_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
     algumas
    0.71
     alguns
    0.69
     alcuni
    0.68
    テレビ
    0.61
     alcune
    0.59
     ニ
    0.59
     ovvero
    0.59
    স
    0.59
     esperienza
    0.58
     niektórych
    0.58
    POSITIVE LOGITS
    led
    0.64
    veillance
    0.55
    -
    0.54
     size
    0.53
    zantine
    0.53
    isor
    0.52
    upyter
    0.52
    zada
    0.52
     sized
    0.51
    le
    0.51
    Activations Density 0.013%

    No Known Activations