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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3996
    Prev
    Next
    INDEX
    Explanations

    World of Warcraft related terms and stats

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    hender
    -0.61
    اقرأ
    -0.52
     Wallflower
    -0.51
     Lordships
    -0.50
     Himo
    -0.50
     ```
    -0.50
    ικά
    -0.49
    خان
    -0.48
    SequentialGroup
    -0.48
     Mos
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.64
    Predecesor
    0.54
    Autoritní
    0.52
    BASELINE
    0.52
    flesh
    0.51
    RetentionPolicy
    0.48
     gorą
    0.47
     känd
    0.47
    OutputType
    0.47
     autorytatywna
    0.46
    Activations Density 8.389%

    No Known Activations