© 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. 127866
    Prev
    Next
    INDEX
    Explanations

    n_estimators

    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
     to
    0.98
    y
    0.87
     the
    0.83
     THE
    0.79
    ;
    0.79
    ก
    0.79
    t
    0.76
     {}
    0.76
     AS
    0.76
    !
    0.76
    POSITIVE LOGITS
    جی
    0.81
    なります
    0.72
    گوید
    0.68
    なる
    0.67
    全ての
    0.67
    یت
    0.66
     می‌تواند
    0.66
    きた
    0.66
    September
    0.65
    اکی
    0.65
    Activations Density 0.000%

    No Known Activations