© 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. 57632
    Prev
    Next
    INDEX
    Explanations

    pencils

    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
     to
    1.42
     was
    1.39
     with
    1.27
    o
    1.20
    led
    1.18
    ke
    1.10
    ka
    1.07
     for
    1.05
    ments
    1.05
    с
    1.05
    POSITIVE LOGITS
    ке
    1.38
    ம்
    1.30
    ﺔ
    1.28
     crece
    1.25
    م
    1.24
    ق
    1.23
     compartilh
    1.23
    ພວກເຮ
    1.21
    ຜະລິດຕະພັນ
    1.21
     architet
    1.21
    Activations Density 0.000%

    No Known Activations