© 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. 5888
    Prev
    Next
    INDEX
    Explanations

    code snippets and database language

    oai_token-act-pair · gemini-2.0-flash

    database IDs

    np_max-act-logits · 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
     propOrder
    -1.20
    NameInMap
    -1.13
    webElementXpaths
    -1.13
    StructEnd
    -1.01
    StoryboardSegue
    -0.95
    sizeCache
    -0.94
    principalColumn
    -0.92
    parsedMessage
    -0.90
     '{@
    -0.90
    MessageOf
    -0.89
    POSITIVE LOGITS
    OrderID
    0.71
    CustomerId
    0.70
    OrderId
    0.66
    PostId
    0.65
    EmployeeId
    0.63
    ProductId
    0.63
    ProductID
    0.59
    CompanyId
    0.57
    CustomerID
    0.57
    CategoryId
    0.57
    Activations Density 6.229%

    No Known Activations