© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9115
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated symbols and words such as punctuation, bullets, HTML, or specific words within quotes (often from legal documents) alongside a few subjective words.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     المعيارى
    -0.67
    TagMode
    -0.63
     متعلقه
    -0.53
    SequentialGroup
    -0.52
    mybatisplus
    -0.51
     تضيفلها
    -0.48
    DoubleQuotes
    -0.47
    MessageTagHelper
    -0.46
    Rüyada
    -0.46
     ExecuteAsync
    -0.45
    POSITIVE LOGITS
     
    0.90
     the
    0.77
     $
    0.69
     “
    0.68
     a
    0.67
    “
    0.67
     "
    0.63
    ”
    0.60
     (
    0.60
     }^{[
    0.59
    Activations Density 21.566%

    No Known Activations