© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 817
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving variables

    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_39_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
    rvGroup
    0.28
    ્લે
    0.27
     pony
    0.26
     ساين
    0.26
     childbirth
    0.25
     irritability
    0.25
     sizeable
    0.25
     poncho
    0.24
    枺
    0.24
    ीण
    0.24
    POSITIVE LOGITS
    log
    0.22
    MB
    0.22
    ö
    0.22
    mb
    0.21
    ‾
    0.21
    V
    0.21
    value
    0.21
    ql
    0.21
    žem
    0.21
    2
    0.21
    Activations Density 0.033%

    No Known Activations