© 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. 955
    Prev
    Next
    INDEX
    Explanations

    medications help protect

    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
    阻
    0.52
     disrupted
    0.50
     difficulty
    0.49
    difficulty
    0.48
     hindered
    0.48
     disrupt
    0.47
     Difficulty
    0.46
    imped
    0.46
    Difficulty
    0.46
     diffic
    0.46
    POSITIVE LOGITS
     exempt
    0.47
     保護
    0.46
     Protect
    0.43
    免
    0.43
     보호
    0.42
    exempt
    0.42
    Prevention
    0.42
    援助
    0.42
     Prevention
    0.41
     Protecting
    0.41
    Activations Density 0.013%

    No Known Activations