© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related text with Portuguese words intermixed

    oai_token-act-pair · gemini-2.0-flash

    non-English language text

    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
    jména
    -0.54
    geslacht
    -0.54
    Footnote
    -0.53
     Référence
    -0.52
     sumpay
    -0.51
    الإنجليزية
    -0.51
    ритори
    -0.50
    WithIOException
    -0.50
     SwitchCompat
    -0.50
    Datuak
    -0.50
    POSITIVE LOGITS
    O
    0.60
    #![
    0.60
     o
    0.59
    webElementXpaths
    0.58
     O
    0.56
    setupUi
    0.51
    ogaster
    0.51
    เศ
    0.50
    routeProvider
    0.47
    initComponents
    0.45
    Activations Density 0.536%

    No Known Activations