© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156172
    Prev
    Next
    INDEX
    Explanations

    Benchmarks

    np_max-act-logits · gemini-2.5-flash-lite
    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
    benzoyl
    0.49
    บา
    0.40
    Д
    0.40
    벤
    0.38
     Bens
    0.38
     Бен
    0.37
     BEN
    0.37
     endowments
    0.36
    ДА
    0.36
     occ
    0.35
    POSITIVE LOGITS
     retr
    0.41
    govor
    0.40
    బు
    0.39
    лён
    0.38
     communiqué
    0.38
    crackers
    0.37
    滲
    0.37
    front
    0.36
     हमारी
    0.36
    تاح
    0.36
    Activations Density 0.000%

    No Known Activations