© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80748
    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_0_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
    is
    2.02
    ل
    2.00
    ल
    1.90
    म
    1.66
    ER
    1.56
    ן
    1.55
    i
    1.52
    l
    1.48
    م
    1.47
    in
    1.45
    POSITIVE LOGITS
    та
    1.43
    си
    1.42
     раствор
    1.41
     sustancias
    1.35
    ﻧ
    1.34
     sắc
    1.33
     stanovnika
    1.26
    んは
    1.25
    ຮັບ
    1.25
    ၊
    1.25
    Activations Density 0.000%

    No Known Activations