© 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. 35784
    Prev
    Next
    INDEX
    Explanations

    hello koala

    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
    Kota
    0.43
    لوم
    0.40
     zuz
    0.39
    console
    0.39
    bours
    0.38
    PELL
    0.37
    тому
    0.37
    룬
    0.37
    uric
    0.37
    옅
    0.37
    POSITIVE LOGITS
     Cor
    0.39
     şeyler
    0.38
     Gregg
    0.37
    iffel
    0.36
    দায়
    0.36
     defendants
    0.36
    тического
    0.35
     corrugated
    0.35
    द्दी
    0.34
     screw
    0.34
    Activations Density 0.002%

    No Known Activations