© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15282
    Prev
    Next
    INDEX
    Explanations

    slot . , FALSE

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Heights
    0.54
    もう
    0.53
     ERK
    0.53
    ତ୍
    0.49
     headaches
    0.48
     ardu
    0.47
    टाम
    0.47
    ی
    0.46
    𝗽
    0.46
    ルの
    0.46
    POSITIVE LOGITS
     edição
    0.52
                       
    0.47
            
    0.46
     möglich
    0.44
     esté
    0.44
     Crane
    0.42
                 
    0.41
     zeigt
    0.41
                        
    0.41
             
    0.40
    Activations Density 0.000%

    No Known Activations