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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12032
    Prev
    Next
    INDEX
    Explanations

    a lot of different things and is likely a garbage neuron

    oai_token-act-pair · gemini-2.0-flash

    specialized medical terminology

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

    ordered

    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
    !
    -0.61
    ↵↵
    -0.55
    ()
    -0.52
    ca
    -0.50
    ->
    -0.49
    !(
    -0.49
    '
    -0.48
    .
    -0.48
     u
    -0.48
    =
    -0.48
    POSITIVE LOGITS
    AndEndTag
    1.21
     تضيفلها
    1.21
     виправивши
    1.19
     متعلقه
    1.14
    IntoConstraints
    1.11
     Мексичка
    1.04
     تانيه
    1.03
    GEBURTSDATUM
    1.03
    featureID
    1.03
    Portail
    1.03
    Activations Density 10.816%

    No Known Activations