© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155801
    Prev
    Next
    INDEX
    Explanations

    s or possessive

    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_60_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
     ve
    2.39
     Vega
    1.87
     VE
    1.83
    Vega
    1.73
     Ve
    1.46
     m
    1.44
    Ve
    1.43
    vega
    1.17
    VE
    1.14
     re
    1.13
    POSITIVE LOGITS
                
    0.56
     s
    0.49
     স
    0.46
     س
    0.45
    s
    0.43
     स
    0.42
                 
    0.41
    arente
    0.38
    arne
    0.36
               
    0.36
    Activations Density 0.019%

    No Known Activations