© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 293
    Prev
    Next
    INDEX
    Explanations

    terms related to app-based taxi services and online shopping

    oai_token-act-pair · gemini-2.0-flash

    Apps and online applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    fromnode
    -0.61
    complexContent
    -0.58
    featureID
    -0.57
    resizingMask
    -0.54
    Referanser
    -0.53
    webElementXpaths
    -0.49
    PostInfinity
    -0.48
    tagext
    -0.47
    writeFieldEnd
    -0.47
    bearers
    -0.47
    POSITIVE LOGITS
     المعيارى
    0.61
     anonym
    0.54
     online
    0.52
     Ancestry
    0.51
    PRNewswire
    0.51
     platforms
    0.50
    orithmic
    0.49
    .*")]
    0.48
     />,
    0.48
     Vergine
    0.48
    Activations Density 0.909%

    No Known Activations