© 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. 2753
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated words, possibly from different languages or contexts, with a strong affinity for the word "supra" and elements of medical or mathematical terminology.

    oai_token-act-pair · gemini-2.0-flash

    machine generated text

    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
     M
    -0.48
    Географи
    -0.48
     why
    -0.47
     F
    -0.46
     disposer
    -0.46
     Me
    -0.46
     le
    -0.45
     Em
    -0.45
     Are
    -0.45
     "
    -0.44
    POSITIVE LOGITS
     betweenstory
    1.09
    RegressionTest
    0.94
     Италијани
    0.89
    RenderAtEndOf
    0.79
    TintMode
    0.76
    новниш
    0.75
    AddTagHelper
    0.73
    SequentialGroup
    0.71
    InitVars
    0.71
    发表于
    0.71
    Activations Density 1.716%

    No Known Activations