© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163764
    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
     편리
    0.40
     conocemos
    0.40
     temos
    0.38
     tenemos
    0.37
    सान
    0.37
    }+{\
    0.37
    лян
    0.37
     dena
    0.36
     अनजान
    0.36
    聁
    0.36
    POSITIVE LOGITS
    ale
    0.41
     bisa
    0.41
    re
    0.41
    Could
    0.40
    could
    0.40
     Could
    0.39
    Can
    0.38
    Account
    0.38
     Books
    0.38
    şı
    0.38
    Activations Density 0.000%

    No Known Activations