© 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. 9392
    Prev
    Next
    INDEX
    Explanations

    mathematical and chemical symbols, especially those indicating exponents and ions

    oai_token-act-pair · gemini-2.0-flash

    Exponents and subtraction symbols

    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
    awtextra
    -0.84
    EndGlobalSection
    -0.81
    DockStyle
    -0.78
    interopRequire
    -0.76
     noDo
    -0.71
    LookAnd
    -0.70
    ugeot
    -0.69
    AnchorStyles
    -0.68
    Pratique
    -0.67
    úsqueda
    -0.67
    POSITIVE LOGITS
    are
    0.46
    JdbcTemplate
    0.45
    UnitTesting
    0.44
    号
    0.44
    mo
    0.43
    ’
    0.43
    lasty
    0.43
    InputStream
    0.42
     /**
    0.42
    號
    0.42
    Activations Density 1.178%

    No Known Activations