© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196278
    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_50_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
    renew
    0.43
     théorème
    0.42
    sluš
    0.40
    getNode
    0.40
    viewDidLoad
    0.39
    Nuclear
    0.39
    renewal
    0.39
    ”:
    0.38
     selenium
    0.38
    තර
    0.38
    POSITIVE LOGITS
     النا
    0.42
     八
    0.41
    вости
    0.39
     КО
    0.38
    八
    0.38
     breakouts
    0.37
     breakout
    0.36
     Neo
    0.36
     வாச
    0.35
    azze
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.