© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36901
    Prev
    Next
    INDEX
    Explanations

    hybrid molecules

    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_31_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
    学者
    0.43
    學者
    0.39
     educating
    0.34
     enrollment
    0.33
     inviting
    0.33
    Invocation
    0.33
    անում
    0.33
     deleniti
    0.32
     學
    0.32
    colorChoice
    0.32
    POSITIVE LOGITS
     Bean
    0.43
     curse
    0.42
    nění
    0.42
    ென்று
    0.41
    bake
    0.40
    ить
    0.40
     sfor
    0.39
     Bé
    0.39
     собрать
    0.38
     bean
    0.37
    Activations Density 0.003%

    No Known Activations