© 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. 238648
    Prev
    Next
    INDEX
    Explanations

    I am/have/possess

    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
     competed
    0.37
     SX
    0.37
    achella
    0.36
     CER
    0.36
     במס
    0.36
     setSnackbar
    0.36
     SCS
    0.36
     DRA
    0.35
     PCS
    0.35
    䇢
    0.35
    POSITIVE LOGITS
    &=&
    0.37
     zostanie
    0.37
    ros
    0.36
    ឹង
    0.36
    зии
    0.36
    embro
    0.35
    Burn
    0.35
     جلد
    0.35
    )}=
    0.35
    Fabric
    0.35
    Activations Density 0.001%

    No Known Activations