© 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. 4033
    Prev
    Next
    INDEX
    Explanations

    difficulty, complexity, effort

    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_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
     easy
    1.06
     Easy
    0.96
    Easy
    0.96
    easy
    0.94
     fácil
    0.88
    容易
    0.88
     легко
    0.87
     fáciles
    0.84
    易
    0.83
     facile
    0.82
    POSITIVE LOGITS
     difficult
    1.57
     difícil
    1.40
     difficile
    1.40
    difficult
    1.38
     трудно
    1.36
     difíciles
    1.31
    Difficult
    1.30
     khó
    1.28
     diffic
    1.28
     Difficult
    1.28
    Activations Density 0.164%

    No Known Activations