© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32980
    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_40_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
     System
    0.38
     med
    0.38
    系統
    0.38
    衔
    0.37
     Öff
    0.37
     OTP
    0.37
     CTO
    0.37
    №
    0.36
    鎮
    0.36
     Quezon
    0.35
    POSITIVE LOGITS
    Totals
    0.41
    =\$
    0.39
    Final
    0.38
     پایه
    0.37
    Circle
    0.36
    عرِّف
    0.36
    Dl
    0.36
    Rem
    0.36
     Locking
    0.36
    Detect
    0.36
    Activations Density 0.000%

    No Known Activations