© 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. 8317
    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
     قاف
    0.31
    Haan
    0.31
    ্না
    0.31
    Sear
    0.31
    ambarkan
    0.30
    μων
    0.30
    Cross
    0.29
    ++];
    0.29
    ORIENT
    0.29
    Loop
    0.29
    POSITIVE LOGITS
     dismiss
    0.38
     പ്രതിഷേധ
    0.36
     entertain
    0.35
     police
    0.35
     Police
    0.35
     Watching
    0.34
     entertaining
    0.33
     gladi
    0.33
    police
    0.32
     protest
    0.32
    Activations Density 0.003%

    No Known Activations