© 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. 10036
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing, particularly colors or styles.

    oai_token-act-pair · gemini-2.0-flash

    clothing

    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
     Pair
    -0.92
     pair
    -0.89
     pairs
    -0.82
    setVerticalGroup
    -0.82
     CreateTagHelper
    -0.81
     PAIR
    -0.78
     Pairs
    -0.77
    kháu
    -0.77
    Pair
    -0.76
    IUrlHelper
    -0.74
    POSITIVE LOGITS
     EconPapers
    0.52
    ագրություններ
    0.52
    .*")]
    0.47
    awaiter
    0.47
     point
    0.46
     C
    0.45
     diverse
    0.43
    Car
    0.43
    glLoadIdentity
    0.43
    OrEqual
    0.43
    Activations Density 1.031%

    No Known Activations