© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3718
    Prev
    Next
    INDEX
    Explanations

    code snippets, comments, or special characters within code

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "you"

    np_token-act-pair-logits · gpt-4o-mini

    your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ujednoznacz
    -0.69
    Демографія
    -0.63
    XmlAccessType
    -0.60
     виправивши
    -0.60
    WebElementEntity
    -0.59
     him
    -0.58
    Demografie
    -0.56
    alanya
    -0.55
     InputDecoration
    -0.54
     cherchés
    -0.54
    POSITIVE LOGITS
     your
    2.53
    your
    2.19
    Your
    2.13
     Your
    2.05
     you
    2.03
     yourself
    1.93
     YOUR
    1.80
    YOUR
    1.78
     yours
    1.75
    你的
    1.71
    Activations Density 0.630%

    No Known Activations