© 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. 1238
    Prev
    Next
    INDEX
    Explanations

    references to historical treaties and laws

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    AndEndTag
    -0.60
    didSet
    -0.56
    InjectAttribute
    -0.55
     nakalista
    -0.52
    IActionResult
    -0.51
     mergeFrom
    -0.50
    awtextra
    -0.50
    ểu
    -0.49
    endphp
    -0.48
    ImageContext
    -0.48
    POSITIVE LOGITS
     parlant
    0.57
    eraard
    0.56
    operating
    0.55
    Teraz
    0.54
     حالا
    0.53
    titleMargin
    0.50
    wns
    0.49
    Positioned
    0.48
     ralla
    0.48
     Carls
    0.47
    Activations Density 4.796%

    No Known Activations