© 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. 11838
    Prev
    Next
    INDEX
    Explanations

    statements and theorems in technical documents

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms and labels

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

    to be

    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
    msgTypes
    -0.52
    let
    -0.44
    elseif
    -0.42
    relle
    -0.41
    pubs
    -0.41
    ishw
    -0.41
    getAs
    -0.39
    oday
    -0.38
    player
    -0.37
    ley
    -0.36
    POSITIVE LOGITS
    تقاوى
    1.05
     pinulongan
    0.91
    Sucesor
    0.86
    WebVitals
    0.85
    ValueStyle
    0.80
    Portale
    0.78
    Архівовано
    0.71
    GEBURTSDATUM
    0.71
    ResumeLayout
    0.70
     kaarangay
    0.69
    Activations Density 4.503%

    No Known Activations