© 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. 27111
    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
     منظم
    0.37
     stabile
    0.36
    әт
    0.36
     Lil
    0.35
     بعمل
    0.35
    ∂</
    0.35
    searchDisplay
    0.35
     stabilized
    0.35
     }{}_{\
    0.34
    BIND
    0.34
    POSITIVE LOGITS
     fundamental
    0.82
     Fundamental
    0.75
    Fundamental
    0.73
    fundamental
    0.68
     fundamentally
    0.66
     фундамента
    0.63
     fondamentale
    0.61
     fondamental
    0.59
     fundamentales
    0.57
     fondamentali
    0.56
    Activations Density 0.019%

    No Known Activations