© 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. 178276
    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
    PathDirectory
    0.44
    䀓
    0.41
    ﻵ
    0.39
    ര്യ
    0.39
    ₡
    0.37
     appellee
    0.37
    ClientID
    0.36
    隱
    0.36
    IDAE
    0.36
     intruder
    0.36
    POSITIVE LOGITS
     SCT
    0.38
    John
    0.38
     vertically
    0.37
     Intern
    0.37
     Talk
    0.37
     বদি
    0.37
     পড়তে
    0.37
     रखो
    0.36
     translate
    0.36
     brutally
    0.36
    Activations Density 0.000%

    No Known Activations