© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48162
    Prev
    Next
    INDEX
    Explanations

    devil, evil, and sins

    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_31_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
    Bishop
    0.51
     bishops
    0.50
     bishop
    0.48
     Bishop
    0.46
     Bishops
    0.45
     episcop
    0.42
     episcopal
    0.42
    bishop
    0.41
     Archbishop
    0.40
    谱
    0.39
    POSITIVE LOGITS
     chiller
    0.39
    炭
    0.37
     almu
    0.36
    aghetti
    0.35
     diabetics
    0.35
     presum
    0.34
     жена
    0.34
    ጥ
    0.34
     diabet
    0.34
    ิ้ง
    0.33
    Activations Density 0.002%

    No Known Activations