© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200782
    Prev
    Next
    INDEX
    Explanations

    repeating 3s

    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_12_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
    l
    0.73
    <strong>
    0.69
                
    0.62
         
    0.61
                    
    0.59
                 
    0.54
                  
    0.54
     April
    0.54
     EVENTS
    0.53
        
    0.52
    POSITIVE LOGITS
    grund
    0.56
    کرد
    0.54
    isé
    0.52
    ts
    0.50
    édia
    0.50
    ته
    0.50
    ků
    0.50
    kB
    0.49
    agement
    0.49
    plum
    0.49
    Activations Density 0.001%

    No Known Activations