© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5662
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to water and related activities

    oai_token-act-pair · gemini-2.0-flash

    terms related to transportation or vehicles

    np_token-act-pair-logits · gpt-4o-mini

    boats and planes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCulture
    -0.66
    MLLoader
    -0.60
    脚注の使い方
    -0.59
     елның
    -0.57
     Lush
    -0.56
    QPalette
    -0.56
    HasAnnotation
    -0.56
     replen
    -0.55
     تكبرها
    -0.55
    참고
    -0.54
    POSITIVE LOGITS
    ThroughAttribute
    0.78
     umano
    0.52
     plane
    0.48
     PLANE
    0.47
     bateaux
    0.46
     fibra
    0.45
     planes
    0.45
     fiber
    0.45
    Encyklopedia
    0.43
    Tracce
    0.43
    Activations Density 1.357%

    No Known Activations