© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217368
    Prev
    Next
    INDEX
    Explanations

    moderate moderation

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attracts
    0.39
    yng
    0.37
    escue
    0.35
    buch
    0.35
    ogel
    0.35
     قریب
    0.34
    ojan
    0.34
    驱
    0.34
    boro
    0.33
    ECTOR
    0.33
    POSITIVE LOGITS
     уме
    1.98
     moderate
    1.37
     Moderate
    1.33
    Moderate
    1.33
    moderate
    1.21
     moderately
    1.20
     помі
    1.18
     umi
    1.16
     moder
    1.12
     moderation
    1.06
    Activations Density 0.001%

    No Known Activations