© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247430
    Prev
    Next
    INDEX
    Explanations

    model`predict(X_test)`

    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_40_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
    ristown
    0.40
     ionization
    0.40
    richter
    0.39
    ussion
    0.39
    Coords
    0.38
     chàng
    0.37
     новой
    0.37
     mineralization
    0.36
    ensee
    0.35
    ®
    0.35
    POSITIVE LOGITS
    Ending
    0.38
     ESP
    0.37
    围
    0.37
     Cherry
    0.37
     espacial
    0.37
    čky
    0.36
    Cherry
    0.36
     Treatment
    0.35
     Treatments
    0.35
     dct
    0.35
    Activations Density 0.002%

    No Known Activations