© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8510
    Prev
    Next
    INDEX
    Explanations

    words related to health and food, especially in the context of promoting health to families in particular

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ngdoc
    -0.65
    økt
    -0.57
    万美元
    -0.56
    ISupport
    -0.55
     lenker
    -0.54
     esterni
    -0.54
     Gaylord
    -0.54
    WidgetItem
    -0.53
    المناصب
    -0.53
     pymongo
    -0.53
    POSITIVE LOGITS
     Wikispecies
    0.61
    "]));
    0.59
     متعلقه
    0.59
     Labor
    0.58
     aged
    0.58
     WA
    0.55
     Aged
    0.51
     Coalition
    0.48
    badah
    0.48
     Reserve
    0.48
    Activations Density 8.562%

    No Known Activations