© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5436
    Prev
    Next
    INDEX
    Explanations

    feature descriptor

    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_39_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
                
    0.50
     '../../../
    0.50
                 
    0.48
     १८४
    0.43
    ----------
    0.43
    ../../../
    0.43
               
    0.42
    0.41
     покра
    0.41
    0.40
    POSITIVE LOGITS
          
    0.43
           
    0.41
    ɡ
    0.38
    ……
    0.37
     দেবেন
    0.37
     playback
    0.36
    十一
    0.36
    ❹
    0.36
    ......
    0.35
     participated
    0.35
    Activations Density 0.039%

    No Known Activations