© 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. 33246
    Prev
    Next
    INDEX
    Explanations

    received good news

    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
    cars
    0.66
    cq
    0.63
    0.62
    cities
    0.61
    accoon
    0.61
    cett
    0.60
    cji
    0.59
    kker
    0.59
     insufficiency
    0.59
    ator
    0.58
    POSITIVE LOGITS
    い
    0.77
     confronto
    0.71
    ي
    0.71
     for
    0.66
    ้
    0.66
    י
    0.65
    ת
    0.65
     provare
    0.64
     Valores
    0.64
    ৮
    0.64
    Activations Density 0.038%

    No Known Activations