© 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. 3758
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting strings used in programming

    oai_token-act-pair · gemini-2.0-flash

    say "s"

    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
    s
    -1.13
    t
    -0.80
    e
    -0.57
    itemBuilder
    -0.55
    brainly
    -0.52
    ים
    -0.50
    ات
    -0.49
    ς
    -0.49
    es
    -0.49
    dı
    -0.48
    POSITIVE LOGITS
    saus
    0.54
     transfieras
    0.54
     defStyle
    0.54
    queryInterface
    0.52
     ویکی‌پدی
    0.50
    TextBoxColumn
    0.49
     Wiktionnaire
    0.48
    verd
    0.48
    blame
    0.48
    rawDesc
    0.47
    Activations Density 6.235%

    No Known Activations