© 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. 168663
    Prev
    Next
    INDEX
    Explanations

    death of

    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
     gerekti
    0.39
     Livingstone
    0.38
    PropertyList
    0.38
     এখানকার
    0.37
    leur
    0.35
    ﺏ
    0.35
    Stories
    0.35
    RAchievement
    0.34
     chast
    0.34
     wody
    0.34
    POSITIVE LOGITS
    ocide
    0.46
     pooling
    0.43
     同
    0.42
     实现
    0.41
     collaborating
    0.41
     imperialism
    0.40
    诞生
    0.38
    axal
    0.38
     تعین
    0.38
     HOM
    0.37
    Activations Density 0.000%

    No Known Activations