© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77449
    Prev
    Next
    INDEX
    Explanations

    sum of numbers

    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_29_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
    ренного
    0.36
    Omn
    0.34
     incrementar
    0.34
    羙
    0.33
     पचा
    0.33
     TSR
    0.32
     trz
    0.31
    ahankan
    0.31
    <0x16>
    0.31
    ्याचा
    0.31
    POSITIVE LOGITS
    روس
    0.32
     admissibility
    0.30
     BoxFit
    0.30
     nervously
    0.29
    setKeepCallback
    0.29
    жалуйста
    0.29
     Russia
    0.29
     glazed
    0.29
     boxers
    0.29
    වීම
    0.29
    Activations Density 0.003%

    No Known Activations