© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75478
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     modalities
    0.36
     मेजर
    0.36
     tellus
    0.35
     계획
    0.35
     statues
    0.34
    告诉我
    0.34
    孖
    0.34
     giãn
    0.33
     groupings
    0.33
     தொகுதி
    0.32
    POSITIVE LOGITS
    Rag
    0.40
    ♢
    0.38
    iyasi
    0.38
    vard
    0.37
    साथ
    0.37
     odlu
    0.37
    GLASS
    0.36
     Glass
    0.36
     ইয়াহিয়া
    0.35
    tson
    0.35
    Activations Density 0.000%

    No Known Activations