© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90360
    Prev
    Next
    INDEX
    Explanations

    trusting completely unknown

    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_23_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
     Tobacco
    0.38
     опро
    0.38
     quarry
    0.38
     tobacco
    0.38
    严
    0.37
     quizzes
    0.37
     cer
    0.36
      
    0.36
    æ
    0.35
     Damon
    0.35
    POSITIVE LOGITS
    creativecommons
    0.44
    .\\
    0.39
    icka
    0.39
     fxaa
    0.39
     RECOMMEND
    0.39
    🖕
    0.39
    -\\
    0.39
    /**/*.
    0.38
     buddhav
    0.38
     commits
    0.38
    Activations Density 0.032%

    No Known Activations