© 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. 8288
    Prev
    Next
    INDEX
    Explanations

    text near a variety of parenthesis-like symbols and version/trademark symbols

    oai_token-act-pair · gemini-2.0-flash

    Legal, formal writing

    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
     R
    -1.47
     L
    -1.46
     S
    -1.39
     M
    -1.38
     G
    -1.30
     T
    -1.27
     D
    -1.27
     P
    -1.27
     E
    -1.21
     C
    -1.20
    POSITIVE LOGITS
     initComponents
    0.77
    richTextPanel
    0.50
    LookAnd
    0.49
    queryInterface
    0.49
     protoimpl
    0.47
    InjectAttribute
    0.47
     &___
    0.46
    Geplaatst
    0.46
     Anſ
    0.46
    횟
    0.46
    Activations Density 4.146%

    No Known Activations