© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6886
    Prev
    Next
    INDEX
    Explanations

    seemingly random words, acronyms, and names, scattered throughout the text.

    oai_token-act-pair · gemini-2.0-flash

    Code and character names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    Portale
    -0.90
     indépendante
    -0.72
     étrangère
    -0.69
     AssemblyProduct
    -0.66
     dependencia
    -0.66
     Савезне
    -0.64
     Paglinawan
    -0.60
     lenker
    -0.58
    Personendaten
    -0.57
     chaude
    -0.57
    POSITIVE LOGITS
    XmlAccessType
    0.52
    apimachinery
    0.51
     sân
    0.47
    }));
    0.46
     makeStyles
    0.44
    fieldLabel
    0.44
    vue
    0.44
    ParallelGroup
    0.44
    AddTagHelper
    0.44
    address
    0.42
    Activations Density 0.611%

    No Known Activations