© 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. 57795
    Prev
    Next
    INDEX
    Explanations

    EVs, PHEVs

    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
    在
    1.09
    大
    1.08
    も
    1.05
    もちろん
    0.99
    سو
    0.99
     marrow
    0.98
    ни
    0.97
    d
    0.96
    с
    0.96
    يا
    0.96
    POSITIVE LOGITS
     a
    1.43
     I
    1.34
    {
    1.16
    ار
    1.10
    (
    1.09
    ۹
    1.08
     it
    1.07
     ---------------
    1.05
     NLR
    1.04
    I
    1.02
    Activations Density 0.000%

    No Known Activations