© 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. 11946
    Prev
    Next
    INDEX
    Explanations

    references to academic publications, especially their titles, authors, and publication details like dates and publishers.

    oai_token-act-pair · gemini-2.0-flash

    historical passage

    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
    PRNewswire
    -0.55
    huawei
    -0.55
     Paglinawan
    -0.55
    byshire
    -0.54
    APORE
    -0.52
    isburg
    -0.50
    yeezy
    -0.50
     Hailey
    -0.50
    WebpackPlugin
    -0.50
     Wallflower
    -0.49
    POSITIVE LOGITS
    Thou
    0.55
    FieldBuilder
    0.52
    >{@
    0.49
    SharedDtor
    0.48
    Przypisy
    0.47
    Attributed
    0.45
    Gothic
    0.44
    AccessorTable
    0.44
    Aristotle
    0.43
    SaveChangesAsync
    0.42
    Activations Density 16.876%

    No Known Activations