© 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. 121537
    Prev
    Next
    INDEX
    Explanations

    feature extraction

    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
     factored
    0.76
    en
    0.70
     фактор
    0.69
     factor
    0.67
    n
    0.65
    ﺎ
    0.64
     factoring
    0.64
     कारक
    0.64
    ed
    0.63
     fatores
    0.61
    POSITIVE LOGITS
    د
    0.75
     of
    0.64
    হাব
    0.63
     Fire
    0.61
     Smaller
    0.58
     Victims
    0.58
     Spirituality
    0.57
     Custom
    0.56
    Icons
    0.56
    gados
    0.56
    Activations Density 0.002%

    No Known Activations