© 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. 33576
    Prev
    Next
    INDEX
    Explanations

    widget build

    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
     stable
    0.45
    stoff
    0.40
    стом
    0.40
     venture
    0.39
     unique
    0.39
     inner
    0.39
     ResourceManager
    0.38
    内
    0.38
     dependable
    0.38
     internos
    0.37
    POSITIVE LOGITS
     raíz
    0.38
     ಗ್ರಾಮ
    0.38
     अध्यक्षता
    0.37
    RootDir
    0.37
     наличи
    0.37
    Village
    0.37
    著作
    0.37
     librería
    0.37
     árbol
    0.36
    RenderTarget
    0.36
    Activations Density 0.004%

    No Known Activations