© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2565
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the availability and distribution of published works, especially limited editions.

    oai_token-act-pair · gemini-2.0-flash

    limited editions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ReusableCell
    -0.71
    
    -0.64
    dymyr
    -0.62
     naviguant
    -0.58
    ölkerung
    -0.58
     förm
    -0.58
     ostavi
    -0.57
     dépla
    -0.57
    MessageTagHelper
    -0.57
     spôso
    -0.57
    POSITIVE LOGITS
    RunAsync
    0.57
    Autoritní
    0.57
    AddTagHelper
    0.48
    PostExecute
    0.42
    Impression
    0.41
    perrt
    0.41
    RequestMethod
    0.40
    pexpr
    0.40
    endphp
    0.40
    usão
    0.39
    Activations Density 0.550%

    No Known Activations