© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14637
    Prev
    Next
    INDEX
    Explanations

    fragments of words such as file, life, or conference

    oai_token-act-pair · gemini-2.0-flash

    ey

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    openqa
    -0.63
     "..\..\
    -0.60
    łaj
    -0.58
    
    -0.56
    mbggenerated
    -0.55
    UnitTesting
    -0.55
     otomatig
    -0.54
    saraba
    -0.53
    </caption>
    -0.52
    ParallelGroup
    -0.52
    POSITIVE LOGITS
    E
    0.69
    е
    0.67
     e
    0.66
    é
    0.66
     eis
    0.65
    esp
    0.64
    getE
    0.64
    è
    0.64
    echa
    0.62
    estat
    0.62
    Activations Density 2.038%

    No Known Activations