© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217492
    Prev
    Next
    INDEX
    Explanations

    Jun or variations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ोध्या
    0.42
    Kam
    0.40
    Rim
    0.39
     UT
    0.39
    ালো
    0.38
    Polar
    0.38
    架
    0.38
     খানকে
    0.38
     kav
    0.37
     chamber
    0.37
    POSITIVE LOGITS
     attend
    0.40
    irre
    0.39
    ieu
    0.39
    GBuf
    0.39
    ãn
    0.37
     বট
    0.36
    irnya
    0.36
    %")
    0.36
     పెట్ట
    0.35
    COMDAT
    0.35
    Activations Density 0.000%

    No Known Activations