© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12642
    Prev
    Next
    INDEX
    Explanations

    code and structured document markup

    oai_token-act-pair · gemini-2.0-flash

    Code/symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Theſe
    -0.66
    MethodImpl
    -0.64
     kaarangay
    -0.61
     houſe
    -0.57
    شهاد
    -0.56
     Houſe
    -0.56
     myſelf
    -0.55
    astify
    -0.54
     Efq
    -0.53
    aminen
    -0.52
    POSITIVE LOGITS
    ↵↵
    0.70
    таратура
    0.65
    ↵
    0.61
    endphp
    0.59
    AutoField
    0.57
    enumi
    0.57
    ynb
    0.54
    ↵↵↵
    0.50
     שוליים
    0.48
    verwijspagina
    0.47
    Activations Density 1.677%

    No Known Activations