© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12878
    Prev
    Next
    INDEX
    Explanations

    the letter mu (μ) and words related to crafting

    oai_token-act-pair · gemini-2.0-flash

    Math/physics equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -0.66
    లాలు
    -0.63
    THISDAY
    -0.59
     GlobalKey
    -0.59
    исленность
    -0.59
     Wiktionnaire
    -0.57
    Życiorys
    -0.57
    migrationBuilder
    -0.56
     Sumter
    -0.54
    ConverterFactory
    -0.53
    POSITIVE LOGITS
    клопе
    0.49
    InSection
    0.48
    円
    0.48
    ⇑
    0.46
     Normdatei
    0.46
    leſs
    0.46
     <",
    0.45
     ویکی‌پدیای
    0.45
     transférez
    0.44
    CAPTION
    0.43
    Activations Density 0.010%

    No Known Activations