© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254227
    Prev
    Next
    INDEX
    Explanations

    level

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ຫຼື
    0.42
    älfte
    0.42
    ৃত্ব
    0.42
    惫
    0.41
    ='%
    0.40
     X
    0.39
    -%
    0.39
    𝑋
    0.39
    的效果
    0.38
     Eugenio
    0.38
    POSITIVE LOGITS
     Up
    0.67
    Up
    0.66
     업
    0.61
     dependence
    0.59
    UP
    0.57
     उप
    0.57
     up
    0.56
     зависимости
    0.56
     UP
    0.55
    up
    0.53
    Activations Density 0.001%

    No Known Activations