© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12364
    Prev
    Next
    INDEX
    Explanations

    name origin or meaning snippets and abbreviations like "or"

    oai_token-act-pair · gemini-2.0-flash

    names or place names

    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
     Monfieur
    -1.09
     myſelf
    -0.91
     Efq
    -0.90
    iffance
    -0.84
    ^(@)
    -0.81
     itſelf
    -0.81
     raiſ
    -0.79
     themſelves
    -0.78
    initely
    -0.76
     leſs
    -0.75
    POSITIVE LOGITS
    j
    0.57
    U
    0.56
    Z
    0.53
    le
    0.52
    ap
    0.51
    •
    0.50
     ap
    0.50
    se
    0.50
    J
    0.50
    Y
    0.49
    Activations Density 0.701%

    No Known Activations