© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96950
    Prev
    Next
    INDEX
    Explanations

    `responsibility` `to` `regarding` `for` `ethical` `AI`

    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_14_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
    -
    0.19
    ad
    0.19
    </h1>
    0.18
                                   
    0.18
    </h2>
    0.18
        
    0.17
    ↵↵
    0.17
       
    0.17
     compliance
    0.16
     م
    0.15
    POSITIVE LOGITS
     energia
    0.20
     에너지
    0.20
     energie
    0.17
     Energie
    0.17
     एनर्जी
    0.17
     энергия
    0.17
     énerg
    0.17
    chloride
    0.17
     фактор
    0.17
     الطاقة
    0.17
    Activations Density 0.014%

    No Known Activations