© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41370
    Prev
    Next
    INDEX
    Explanations

    equality or assignment

    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_11_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
    t
    0.70
    y
    0.61
    i
    0.59
    G
    0.59
    m
    0.57
    vacc
    0.54
    et
    0.54
    grat
    0.54
    Vacc
    0.53
    l
    0.53
    POSITIVE LOGITS
     carboxylic
    0.61
     HNO
    0.58
     ชม
    0.57
     elution
    0.57
    🖒
    0.57
    በባ
    0.56
    pcid
    0.56
     Мини
    0.55
     deme
    0.55
     Schottky
    0.55
    Activations Density 0.000%

    No Known Activations