© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209597
    Prev
    Next
    INDEX
    Explanations

    annual financial reports

    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_5_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
     a
    1.08
    in
    1.02
    0.79
     innervation
    0.79
    кою
    0.79
    inę
    0.78
    mi
    0.75
    bahan
    0.75
    azione
    0.71
     przede
    0.71
    POSITIVE LOGITS
    0
    1.02
    F
    0.84
    X
    0.84
    ри
    0.84
    J
    0.82
    is
    0.80
    لم
    0.75
    िंग
    0.74
     Daten
    0.74
    ០
    0.74
    Activations Density 0.002%

    No Known Activations