© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 875
    Prev
    Next
    INDEX
    Explanations

    refusal to describe explicit content

    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_39_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
    Visitation
    0.40
     divide
    0.36
    感動
    0.36
    Divide
    0.35
     کنکریاں
    0.35
    verse
    0.34
     Divide
    0.34
    onnées
    0.34
    擬
    0.34
     समझौता
    0.33
    POSITIVE LOGITS
    urança
    0.35
    ẋ
    0.32
    हो
    0.32
    ပါ
    0.31
     Turns
    0.31
     DbSet
    0.31
     Ashe
    0.31
     Zane
    0.31
    WAIT
    0.31
    ವ
    0.30
    Activations Density 0.093%

    No Known Activations