© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80834
    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_31_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
     oper
    0.42
    tenant
    0.41
     tenant
    0.40
     plugged
    0.38
    (/
    0.37
     jamming
    0.37
     doomed
    0.37
     norm
    0.36
     plug
    0.36
     Plug
    0.36
    POSITIVE LOGITS
    钕
    0.45
    バス
    0.42
    瑠
    0.42
     ريد
    0.41
    juna
    0.40
    bus
    0.38
    getResponseCode
    0.38
     كوس
    0.37
     Nessa
    0.37
     кад
    0.37
    Activations Density 0.000%

    No Known Activations