© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33547
    Prev
    Next
    INDEX
    Explanations

    celibacy / involuntary celibacy

    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_3_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
    ᱓
    0.84
    ᱘
    0.82
    ۵
    0.80
    ᱖
    0.75
    infused
    0.72
    ᱜ
    0.71
    ᱙
    0.71
     영향
    0.70
    oarece
    0.69
    populated
    0.69
    POSITIVE LOGITS
     in
    0.85
     (
    0.79
    -
    0.78
     myst
    0.75
     YouTube
    0.74
    เป็น
    0.74
     tri
    0.71
    在
    0.71
     ke
    0.71
     produ
    0.71
    Activations Density 0.000%

    No Known Activations