© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 186
    Prev
    Next
    INDEX
    Explanations

    phrases about normal, healthy, activities and fitness.

    oai_token-act-pair · gemini-2.0-flash

    Currency symbols

    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
     activity
    -1.73
    activity
    -1.62
     Activity
    -1.59
     ACTIVITY
    -1.52
    Activity
    -1.48
    ACTIVITY
    -1.38
     Activities
    -1.34
    activities
    -1.32
    Activities
    -1.32
     actividad
    -1.32
    POSITIVE LOGITS
    $
    0.83
    $\
    0.80
    $.
    0.79
    $,
    0.75
    $-
    0.59
    $(
    0.56
    $)
    0.55
    ${\
    0.53
    $=\
    0.53
    $\\
    0.52
    Activations Density 3.145%

    No Known Activations