© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66515
    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_41_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
     Akhtar
    0.40
     التف
    0.38
     pregn
    0.37
     আফজাল
    0.36
    گن
    0.36
     bangun
    0.36
    uncle
    0.35
     士
    0.35
    cutoff
    0.35
     convexes
    0.35
    POSITIVE LOGITS
     rack
    2.34
     Rack
    2.17
    Rack
    2.14
     racks
    2.08
     racking
    1.95
    rack
    1.95
     racked
    1.86
    ラック
    1.50
     rak
    1.38
    架
    1.30
    Activations Density 0.077%

    No Known Activations