© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121573
    Prev
    Next
    INDEX
    Explanations

    Okay

    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_27_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
     Visualization
    0.39
     No
    0.38
     Simply
    0.38
     visualization
    0.37
     Britain
    0.37
     glut
    0.37
     Imagine
    0.37
     Governor
    0.36
    لح
    0.36
    킵
    0.36
    POSITIVE LOGITS
    つまり
    0.38
    季
    0.37
    Ole
    0.36
    OMA
    0.36
    Mâc
    0.36
    Consistent
    0.36
     बाली
    0.35
    Wet
    0.34
     тобто
    0.34
    PRES
    0.34
    Activations Density 0.033%

    No Known Activations