© 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. 7585
    Prev
    Next
    INDEX
    Explanations

    a variety of common abbreviation-related patterns like initials, short words near parentheses or periods, and certain capitalized words found in citations

    oai_token-act-pair · gemini-2.0-flash

    Academic citations/sources

    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
    <strong>
    -0.57
    <eos>
    -0.51
     “
    -0.51
    //
    -0.51
    ta
    -0.49
     w
    -0.48
    "
    -0.47
     
    -0.47
    sa
    -0.47
     n
    -0.47
    POSITIVE LOGITS
    NameInMap
    1.09
    DockStyle
    1.01
    contentLoaded
    0.98
    thâu
    0.92
    bootstrapcdn
    0.92
     Seeder
    0.91
    ressee
    0.88
    Tikang
    0.88
    yntaxException
    0.87
    kháu
    0.87
    Activations Density 0.780%

    No Known Activations