© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257252
    Prev
    Next
    INDEX
    Explanations

    software and compatibility

    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_22_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
     площади
    0.31
     hydride
    0.31
    โน
    0.31
    数目
    0.30
    妮
    0.30
     ác
    0.29
    omani
    0.28
     cahaya
    0.28
    取决
    0.28
     życia
    0.27
    POSITIVE LOGITS
     Phar
    0.29
     ipt
    0.28
     interoper
    0.27
     ,
    0.27
     DSP
    0.26
     elsewhere
    0.26
    Phi
    0.26
     Weapons
    0.26
     THER
    0.25
    -}$
    0.25
    Activations Density 0.009%

    No Known Activations