Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14900
    Prev
    Next
    INDEX
    Explanations

    words used in programming environments that mention code or libraries

    oai_token-act-pair · gemini-2.0-flash

    code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tagHelperRunner
    -0.60
    ruptedException
    -0.57
    })`
    -0.55
     Италијани
    -0.54
     MainAxisSize
    -0.52
     BoxFit
    -0.52
    MigrationBuilder
    -0.50
    ViewById
    -0.48
    )))));
    -0.48
    weighed
    -0.48
    POSITIVE LOGITS
     Wiktionnaire
    0.57
    nambuco
    0.55
    MockBean
    0.53
     will
    0.49
     تكبرها
    0.49
    outons
    0.49
    BASEPATH
    0.48
    ppia
    0.48
    ValueGeneration
    0.47
    metto
    0.47
    Activations Density 2.745%

    No Known Activations