© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10833
    Prev
    Next
    INDEX
    Explanations

    snippets of HTML code with `hello` near `test`

    oai_token-act-pair · gemini-2.0-flash

    greetings, conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Hi
    -2.25
     Hello
    -2.22
    Hi
    -2.19
    Hello
    -2.03
     hello
    -2.02
     hi
    -1.97
    hello
    -1.69
    hi
    -1.66
     HELLO
    -1.63
    HELLO
    -1.63
    POSITIVE LOGITS
    enumi
    0.71
    XmlType
    0.54
    PropertyGroup
    0.52
    WEBPACK
    0.48
     /\.
    0.48
     StatelessWidget
    0.45
    PageContext
    0.45
    的世界
    0.43
    Демографія
    0.42
     Bourg
    0.42
    Activations Density 0.596%

    No Known Activations