© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13651
    Prev
    Next
    INDEX
    Explanations

    phrases that connect or relate certain concepts

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    quels
    -0.77
    enumi
    -0.59
    quelles
    -0.52
     Which
    -0.50
    acquisto
    -0.48
    Demografía
    -0.48
    chability
    -0.46
    ζει
    -0.45
    Maße
    -0.44
     there
    -0.44
    POSITIVE LOGITS
     that
    2.56
     bahwa
    1.70
    that
    1.56
     rằng
    1.53
     że
    1.38
     bahawa
    1.30
     dass
    1.28
     ότι
    1.24
     kwamba
    1.23
     että
    1.18
    Activations Density 6.693%

    No Known Activations