© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6831
    Prev
    Next
    INDEX
    Explanations

    seemingly random letters and partial words, possibly due to encoding artifacts or looking for specific character sequences within code or identifiers.

    oai_token-act-pair · gemini-2.0-flash

    Jark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.90
    Datuak
    -0.83
    webElementXpaths
    -0.78
    IContainer
    -0.58
     onCreateView
    -0.53
     @"/
    -0.52
    DockStyle
    -0.52
    richTextPanel
    -0.50
     nahilalakip
    -0.48
    Tikang
    -0.47
    POSITIVE LOGITS
    tymologie
    0.63
    CppCodeGen
    0.62
    ̍t
    0.60
     fraî
    0.59
     NDL
    0.59
    +#+#
    0.54
    tahankan
    0.54
     estekak
    0.54
    remera
    0.54
     cherchés
    0.53
    Activations Density 5.394%

    No Known Activations