© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122441
    Prev
    Next
    INDEX
    Explanations

    code structures with `.to` or `.toEqual`

    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_38_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
     karyawan
    0.42
     neglected
    0.41
     n
    0.40
     Indexed
    0.39
     جدا
    0.38
     সম্পর্
    0.37
     xi
    0.37
     不过
    0.37
     ن
    0.36
     collaboration
    0.36
    POSITIVE LOGITS
    Decor
    0.40
    decor
    0.39
    CapsLock
    0.38
     decorators
    0.38
    Quot
    0.37
     Decor
    0.37
     decor
    0.36
     सलामी
    0.36
    טר
    0.36
     detectives
    0.36
    Activations Density 0.000%

    No Known Activations