© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13497
    Prev
    Next
    INDEX
    Explanations

    conjunctions and pronouns, particularly "to" and pronouns referring to people

    oai_token-act-pair · gemini-2.0-flash

    funding, covering expenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Select
    -0.57
     Select
    -0.56
    select
    -0.56
     select
    -0.56
    titleMargin
    -0.50
     المعيارى
    -0.50
    zert
    -0.50
    Hentet
    -0.50
    IVEREF
    -0.48
    χη
    -0.47
    POSITIVE LOGITS
     fund
    0.96
     cover
    0.89
    fund
    0.75
     Fund
    0.74
     Cover
    0.69
    Fund
    0.65
     pack
    0.64
    cover
    0.62
     block
    0.61
    WireFormatLite
    0.59
    Activations Density 4.784%

    No Known Activations