© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8721
    Prev
    Next
    INDEX
    Explanations

    indications and uses

    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_13_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
    j
    0.38
    N
    0.36
    t
    0.35
    av
    0.33
    y
    0.31
    ug
    0.30
    J
    0.29
    X
    0.28
    enyl
    0.28
    en
    0.27
    POSITIVE LOGITS
     conflictos
    0.29
     dhinak
    0.29
     finalidad
    0.28
     காரண
    0.28
    DVRIP
    0.28
     роль
    0.27
     आंबेडकर
    0.27
    铛
    0.27
     аккумуля
    0.27
    ⺠
    0.27
    Activations Density 0.028%

    No Known Activations