© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10730
    Prev
    Next
    INDEX
    Explanations

    grades and school years

    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
    Not in Any Lists

    No Comments

    Negative Logits
    de
    0.64
           
    0.61
          
    0.57
               
    0.53
    他不
    0.53
     (−
    0.51
    ten
    0.50
     („
    0.49
     Специа
    0.49
    Ва
    0.49
    POSITIVE LOGITS
    ף
    0.58
    高校
    0.56
     college
    0.55
     mischief
    0.54
     teenagers
    0.53
     estudantes
    0.52
     students
    0.51
     impediments
    0.50
     untold
    0.49
    mittel
    0.49
    Activations Density 0.008%

    No Known Activations