© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19299
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     خوب
    0.39
     Heating
    0.39
    右上
    0.39
     subtraction
    0.38
    ananti
    0.37
    Theta
    0.37
    stato
    0.37
    Ğ
    0.37
     distin
    0.36
     japan
    0.36
    POSITIVE LOGITS
     Cardinals
    0.69
     कार्ड
    0.63
     Cardinal
    0.62
    Cardinal
    0.62
     Kard
    0.61
     cardinal
    0.59
    card
    0.59
    कार्ड
    0.58
     কার্ড
    0.57
     kard
    0.57
    Activations Density 0.000%

    No Known Activations