© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129771
    Prev
    Next
    INDEX
    Explanations

    surnames

    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_50_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
    ningarna
    0.39
    igheter
    0.38
    نساء
    0.38
     trombone
    0.37
     bisogna
    0.37
    ,]
    0.36
    asjoner
    0.36
    षु
    0.36
     ्
    0.35
     শিষ্য
    0.35
    POSITIVE LOGITS
     Johns
    0.85
     DCs
    0.84
     DNIs
    0.80
     Smiths
    0.75
     Scotts
    0.74
    SCs
    0.74
     earths
    0.73
     Apples
    0.73
     SPMs
    0.73
     YouT
    0.71
    Activations Density 0.000%

    No Known Activations