Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13385
    Prev
    Next
    INDEX
    Explanations

    words/phrases that confirm an idea or opinion is based in reality

    oai_token-act-pair · gemini-2.0-flash

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     real
    -2.78
    real
    -2.48
    Real
    -2.38
     Real
    -2.33
    REAL
    -2.09
     REAL
    -2.06
     réel
    -1.74
     reales
    -1.63
     reale
    -1.59
     réelle
    -1.57
    POSITIVE LOGITS
    HasForeignKey
    0.61
    WaitGroup
    0.59
    ArgumentParser
    0.55
    HomeAsUpEnabled
    0.54
     coussin
    0.53
     Hunger
    0.52
    Trama
    0.52
     CommonModule
    0.51
     setDescription
    0.51
     maîtrise
    0.50
    Activations Density 7.323%

    No Known Activations