© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15321
    Prev
    Next
    INDEX
    Explanations

    words and phrases that connect ideas and/or signal trends

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    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
     increase
    -1.55
     Increase
    -1.50
    Increase
    -1.48
    increase
    -1.44
     increases
    -1.35
     Increases
    -1.32
     increased
    -1.30
     INCREASE
    -1.30
    Increases
    -1.28
     increasing
    -1.27
    POSITIVE LOGITS
    $_['
    0.59
    évaluateur
    0.47
     @"/
    0.46
    Personendaten
    0.45
     estekak
    0.44
    fortawesome
    0.44
    <bos>
    0.43
    OP
    0.43
    ute
    0.43
     ब्रेकडाउन
    0.43
    Activations Density 2.628%

    No Known Activations