© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232203
    Prev
    Next
    INDEX
    Explanations

    wave propagation or physical properties

    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_32_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
     maximum
    0.41
    maximum
    0.40
    }-${
    0.38
     CHAPTER
    0.38
     máxim
    0.38
    ENDPOINT
    0.37
    𝗇
    0.37
    Highest
    0.37
    สูงสุด
    0.37
    屿
    0.37
    POSITIVE LOGITS
     Stack
    0.45
    團隊
    0.44
     Atom
    0.39
    δο
    0.38
     Kut
    0.38
     NAT
    0.37
     Team
    0.37
     stack
    0.37
     actualizado
    0.36
    стор
    0.36
    Activations Density 0.000%

    No Known Activations