© 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. 168113
    Prev
    Next
    INDEX
    Explanations

    (

    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
    надца
    0.38
    Groups
    0.37
    Camping
    0.37
    questao
    0.35
     пе
    0.34
    !!"
    0.34
    camping
    0.34
     ত
    0.33
     मरीज
    0.33
    Эта
    0.33
    POSITIVE LOGITS
     त्रिभु
    0.38
     interstate
    0.37
     cosmology
    0.37
    Interactor
    0.37
     earthquakes
    0.37
     ruining
    0.37
     HelloWorld
    0.36
     adapter
    0.35
     Cosmology
    0.35
     thrones
    0.35
    Activations Density 0.000%

    No Known Activations