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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44080
    Prev
    Next
    INDEX
    Explanations

    reactive oxygen species

    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
     )
    0.83
    도
    0.75
    0.75
    EN
    0.74
    એ
    0.73
    ও
    0.72
    ES
    0.71
    ור
    0.71
     +
    0.70
                    
    0.68
    POSITIVE LOGITS
    كيل
    0.68
    كار
    0.63
    كال
    0.63
    {
    0.62
    وك
    0.58
    krank
    0.56
    पंथी
    0.56
    朋
    0.56
    ర్
    0.55
    مط
    0.55
    Activations Density 0.005%

    No Known Activations