© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10408
    Prev
    Next
    INDEX
    Explanations

    a constellation of words related to personal anecdotes, computing/electronics, sports, healthcare, food, and real estate.

    oai_token-act-pair · gemini-2.0-flash

    personal aspects of life

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     beginnetje
    -0.88
    IntoConstraints
    -0.82
     resourceCulture
    -0.73
     autorytatywna
    -0.72
     CreateTagHelper
    -0.70
    RegressionTest
    -0.69
     quæ
    -0.66
     estekak
    -0.65
     habet
    -0.65
     récomp
    -0.60
    POSITIVE LOGITS
    ancies
    0.52
     situation
    0.50
    MENAFN
    0.50
     process
    0.49
    TabIndex
    0.49
    iches
    0.49
    userdetails
    0.47
    liest
    0.46
     reputation
    0.46
     career
    0.46
    Activations Density 3.493%

    No Known Activations