© 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. 115117
    Prev
    Next
    INDEX
    Explanations

    .com

    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
     Arrays
    0.40
     зер
    0.39
    ೋ
    0.38
     timer
    0.36
     Lecture
    0.35
     densely
    0.35
     androidTest
    0.34
     multipart
    0.34
     स्लाइड्स
    0.34
     soll
    0.34
    POSITIVE LOGITS
    Rho
    0.44
    赃
    0.40
     Rho
    0.39
    Aile
    0.38
     נישט
    0.38
    iume
    0.37
    ateg
    0.37
     BLUEN
    0.37
    लोर
    0.37
    жні
    0.37
    Activations Density 0.002%

    No Known Activations