© 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. 18981
    Prev
    Next
    INDEX
    Explanations

    list items and bullet points

    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
    দ্ম
    0.39
    踺
    0.37
    czeniu
    0.36
    czenia
    0.35
    swim
    0.33
    issam
    0.33
    াড়ি
    0.33
     overfitting
    0.32
    Morris
    0.32
     deodor
    0.31
    POSITIVE LOGITS
    •
    0.91
     •
    0.83
    ・
    0.81
     ・
    0.79
    
    0.79
    ①
    0.79
     ①
    0.79
     
    0.77
     ●
    0.73
    ⦁
    0.70
    Activations Density 0.197%

    No Known Activations