© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19193
    Prev
    Next
    INDEX
    Explanations

    Morocco Tunisia North Africa

    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_40_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
    cle
    0.41
     char
    0.39
     Deviation
    0.38
     IN
    0.38
    裂
    0.38
     Id
    0.37
    fileID
    0.37
    chit
    0.37
    倣
    0.37
    ரம்
    0.37
    POSITIVE LOGITS
    グラン
    0.39
    tonne
    0.36
    Polish
    0.35
    Adams
    0.34
    🏵
    0.34
    Gran
    0.34
     virtuous
    0.34
     ಪಡೆ
    0.33
    সন্ত
    0.33
    ທີ່
    0.33
    Activations Density 0.010%

    No Known Activations