© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170280
    Prev
    Next
    INDEX
    Explanations

    Marvel Cinematic Universe

    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_20_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
    itare
    0.57
    вані
    0.47
    гій
    0.46
    LAGAB
    0.45
    rapes
    0.45
    
    0.44
     কেন্দ্রের
    0.43
     ঈশ্বর
    0.43
     kommt
    0.43
     கிடைத்தது
    0.42
    POSITIVE LOGITS
     b
    0.43
     Sunt
    0.42
     Brim
    0.41
     Laugh
    0.41
     constitutive
    0.40
    um
    0.40
     och
    0.40
     konstit
    0.40
     Crim
    0.39
     Amy
    0.39
    Activations Density 0.001%

    No Known Activations