© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152126
    Prev
    Next
    INDEX
    Explanations

    nearly/almost

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     essentially
    0.59
    essentially
    0.52
     basically
    0.46
     تقريبا
    0.44
    䅞
    0.43
    basically
    0.42
     почти
    0.42
     تقریبا
    0.42
     virtually
    0.41
     splurge
    0.41
    POSITIVE LOGITS
     had
    0.46
    别墅
    0.44
     Had
    0.43
     Always
    0.41
     hadde
    0.41
    短
    0.40
     проекти
    0.38
     added
    0.38
     উষ্ণ
    0.37
     Launched
    0.37
    Activations Density 0.001%

    No Known Activations