© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57711
    Prev
    Next
    INDEX
    Explanations

    eliminating waste, setup, or redundant

    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_2_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
    '
    1.41
    ’
    1.19
    ot
    1.09
    ut
    1.08
    ol
    0.97
    ן
    0.96
    ους
    0.93
    กฏ
    0.93
    akon
    0.93
     Causeway
    0.91
    POSITIVE LOGITS
    る
    1.59
    一
    1.53
    К
    1.52
    d
    1.50
    л
    1.48
    д
    1.48
    ה
    1.45
    a
    1.38
    ד
    1.37
    an
    1.32
    Activations Density 0.005%

    No Known Activations