© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19132
    Prev
    Next
    INDEX
    Explanations

    java utility imports

    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_34_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
    WAN
    0.37
    ᱣ
    0.35
     DEC
    0.35
     केंद्रीय
    0.34
    aded
    0.33
     ADMIN
    0.33
    导
    0.33
     MUR
    0.33
    etal
    0.32
    TRAN
    0.32
    POSITIVE LOGITS
     bonnes
    0.44
     Azores
    0.40
    畤
    0.40
    BagConstraints
    0.38
    稞
    0.38
    िनी
    0.38
     antioxidant
    0.37
     antioxidants
    0.37
     reseñas
    0.37
     buenos
    0.37
    Activations Density 0.000%

    No Known Activations