© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5403
    Prev
    Next
    INDEX
    Explanations

    guarding and protecting

    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_40_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
    电动
    0.43
    辍
    0.38
    mask
    0.37
    Viewer
    0.37
     आपूर्ति
    0.37
     活動
    0.37
    Payments
    0.36
    掻
    0.36
     VIDE
    0.36
     அம்ச
    0.36
    POSITIVE LOGITS
     guarding
    0.59
    守护
    0.55
     guardianship
    0.54
     guardians
    0.49
     guards
    0.49
     guardian
    0.49
    守
    0.47
     guard
    0.46
    guardian
    0.46
     Guard
    0.45
    Activations Density 0.017%

    No Known Activations