© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46499
    Prev
    Next
    INDEX
    Explanations

    data set :id

    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_22_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
     specimens
    0.44
     Jasmine
    0.43
     pubescens
    0.43
    两年
    0.41
    <bos>
    0.40
    apex
    0.40
     statues
    0.39
     stockp
    0.38
     educator
    0.38
    jacoco
    0.38
    POSITIVE LOGITS
     ഗ
    0.43
    Sending
    0.43
    iy
    0.42
     헤
    0.42
    水
    0.42
    헤
    0.42
    fy
    0.42
     HEP
    0.42
    よび
    0.41
    よ
    0.40
    Activations Density 0.005%

    No Known Activations