© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9339
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up" or "ups" appearing nearby a short word like "before" or a hyphen

    oai_token-act-pair · gemini-2.0-flash

    warming up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.62
    arXiv
    -0.44
    eces
    -0.44
     adelantado
    -0.43
    campista
    -0.43
    IActionResult
    -0.43
    eksi
    -0.38
     trinh
    -0.38
     lays
    -0.37
     charité
    -0.36
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.81
    下载附件
    0.75
     propOrder
    0.72
    abestanden
    0.72
    .}\
    0.65
    ništ
    0.63
    SBATCH
    0.63
    numerusform
    0.62
    ILITIES
    0.61
    FormTagHelper
    0.61
    Activations Density 1.262%

    No Known Activations