© 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. 48053
    Prev
    Next
    INDEX
    Explanations

    restroom sanitation features

    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
    reference
    0.45
    Perm
    0.42
    perm
    0.40
     магази
    0.40
    wania
    0.39
    Reference
    0.39
    talking
    0.39
    Talking
    0.38
     }]);
    0.37
     приста
    0.37
    POSITIVE LOGITS
     quang
    0.42
     career
    0.39
     रिक्वायरमेंट
    0.39
     patriarchal
    0.38
    忠
    0.38
     comfortably
    0.38
    ifient
    0.38
     සම
    0.37
    ifiées
    0.37
     quarters
    0.37
    Activations Density 0.002%

    No Known Activations