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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2477
    Prev
    Next
    INDEX
    Explanations

    words and phrases from a range of topics including goodness / mormonism, geometry and design, and neuro-endocrine systems

    oai_token-act-pair · gemini-2.0-flash

    together

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     invokingState
    -0.53
    LogFactory
    -0.47
    ethene
    -0.47
     estimés
    -0.46
    isPrime
    -0.45
    elemField
    -0.45
    IGENCE
    -0.45
    <![
    -0.44
    licó
    -0.44
    Sampled
    -0.44
    POSITIVE LOGITS
     together
    1.43
     Together
    1.34
    Together
    1.34
     saling
    1.33
    together
    1.33
     mutual
    1.28
     elkaar
    1.23
     TOGETHER
    1.21
     mutually
    1.21
     juntos
    1.19
    Activations Density 10.920%

    No Known Activations