© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 128974
    Prev
    Next
    INDEX
    Explanations

    Stop, Mary, Emeryville

    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_1_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
    x
    1.88
    is
    1.52
    S
    1.51
    n
    1.45
    T
    1.43
    j
    1.38
    k
    1.37
    ra
    1.35
    p
    1.35
    it
    1.28
    POSITIVE LOGITS
    ۳
    1.00
    できます
    0.98
    す
    0.98
    下が
    0.98
    یو
    0.96
    上が
    0.94
    αν
    0.93
    ird
    0.91
    rotic
    0.88
    dehyde
    0.87
    Activations Density 0.000%

    No Known Activations