© 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. 91877
    Prev
    Next
    INDEX
    Explanations

    non-destructive / non-profit / non-dom

    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
     aort
    0.72
    எஸ்
    0.68
    یی
    0.66
    oC
    0.65
    ἲ
    0.65
     defaul
    0.64
    어나
    0.63
    inį
    0.63
    lardan
    0.63
    0
    0.63
    POSITIVE LOGITS
    ="
    0.86
    é
    0.85
    ä
    0.74
    of
    0.73
    ст
    0.63
    ang
    0.61
     ଶ
    0.60
    {
    0.59
     policía
    0.59
    illings
    0.59
    Activations Density 0.004%

    No Known Activations