© 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. 12287
    Prev
    Next
    INDEX
    Explanations

    descriptions of how a device is attached to something

    oai_token-act-pair · gemini-2.0-flash

    fixing in place

    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
     ExecuteAsync
    -0.72
    UIApplication
    -0.64
    ReusableCell
    -0.58
    himovic
    -0.57
    ViewImports
    -0.56
     proprement
    -0.55
     &___
    -0.55
     onCancelled
    -0.55
    pherals
    -0.54
     commonwealth
    -0.54
    POSITIVE LOGITS
     autorytatywna
    0.54
    談社
    0.50
     wenden
    0.49
    +:+
    0.48
     Suivez
    0.48
     initComponents
    0.46
    UnknownFields
    0.46
     berdua
    0.46
    quoi
    0.45
    XmlEnum
    0.45
    Activations Density 2.280%

    No Known Activations