© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2250
    Prev
    Next
    INDEX
    Explanations

    product numbers and model numbers.

    oai_token-act-pair · gemini-2.0-flash

    Identifying codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     &___
    -0.82
    expandindo
    -0.81
    رشف
    -0.80
    Controllo
    -0.79
    atguigu
    -0.77
     EconPapers
    -0.77
    aarrggbb
    -0.76
    parsedMessage
    -0.75
    DoubleQuotes
    -0.75
     кӀ
    -0.73
    POSITIVE LOGITS
    
    0.44
     ab
    0.44
     же
    0.43
     stessi
    0.43
     Krieges
    0.42
     فارس
    0.42
    else
    0.39
     sin
    0.39
    det
    0.39
    lø
    0.39
    Activations Density 0.412%

    No Known Activations