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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12358
    Prev
    Next
    INDEX
    Explanations

    mathematical notation/code involving matrices and graphs

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ंदीखरीदारी
    -0.58
    rrggbb
    -0.54
    cepatan
    -0.51
    GroupLayout
    -0.47
     εικό
    -0.47
    RegressionTest
    -0.47
     Testamento
    -0.47
     asiática
    -0.47
    Reklama
    -0.46
    Karol
    -0.45
    POSITIVE LOGITS
    sidemargin
    0.69
     AssemblyCulture
    0.62
     springfox
    0.61
    WebElementEntity
    0.57
    WriteAttribute
    0.57
    setTypeface
    0.56
    Geplaatst
    0.54
     الاطلاع
    0.51
    principalTable
    0.51
     unknownFields
    0.51
    Activations Density 2.798%

    No Known Activations