© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2620
    Prev
    Next
    INDEX
    Explanations

    patterns related to the game World of Warcraft, particularly involving professions like Tailoring and Enchanting, vendor locations, and leveling guides

    oai_token-act-pair · gemini-2.0-flash

    Game item acquisition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.59
     character
    -0.54
    Character
    -0.49
    Downloaded
    -0.47
     Character
    -0.46
    }")
    -0.44
     Barat
    -0.43
    OTH
    -0.40
    }$)
    -0.40
     char
    -0.40
    POSITIVE LOGITS
    Autoritní
    0.95
     betweenstory
    0.83
    
    0.76
     republics
    0.73
    SceneManagement
    0.71
    Rohy
    0.71
     guilds
    0.69
     Verbs
    0.68
     مشين
    0.68
     Provinces
    0.68
    Activations Density 7.313%

    No Known Activations