© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15997
    Prev
    Next
    INDEX
    Explanations

    code snippets, in Java, C#, and other languages

    oai_token-act-pair · gemini-2.0-flash

    +

    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
    3
    -0.47
    M
    -0.46
    LER
    -0.46
    žin
    -0.43
    </strong>
    -0.43
     M
    -0.41
    ma
    -0.41
    rof
    -0.41
     K
    -0.40
    lerc
    -0.40
    POSITIVE LOGITS
     nahilalakip
    1.23
    ValueStyle
    1.23
     مشين
    1.22
    
    1.13
    parsedMessage
    1.11
    MigrationBuilder
    1.09
     تضيفلها
    1.04
     EconPapers
    1.01
    WithIOException
    1.01
    OGND
    1.00
    Activations Density 0.523%

    No Known Activations