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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1087
    Prev
    Next
    INDEX
    Explanations

    language related to international relations, especially those implicating Morocco

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_token-act-pair-logits · gemini-2.0-flash

    Computer code, tech language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    ########.
    -0.65
    dibles
    -0.61
     sondern
    -0.57
    ẹn
    -0.56
    XmlAccessType
    -0.56
    rawdę
    -0.56
     gratific
    -0.56
     fellowships
    -0.55
    Herkunft
    -0.55
    (")");
    -0.55
    POSITIVE LOGITS
    GraphicsUnit
    0.55
     CreateTagHelper
    0.51
    LayoutManager
    0.50
     CURLOPT
    0.50
    matchCondition
    0.47
     ModelExpression
    0.46
    errHandler
    0.45
     EClass
    0.44
    RTLE
    0.44
     https
    0.43
    Activations Density 1.336%

    No Known Activations