© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11363
    Prev
    Next
    INDEX
    Explanations

    chemical terms related to organic chemistry

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds and their properties

    np_token-act-pair-logits · gpt-4o-mini

    Chemical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    -0.77
     typelib
    -0.73
    AsUp
    -0.72
    RegressionTest
    -0.71
    createTextNode
    -0.69
    Демографія
    -0.69
    ьаж
    -0.67
    DockStyle
    -0.63
    UnusedPrivate
    -0.63
    Бахар
    -0.63
    POSITIVE LOGITS
    KeySpec
    0.41
     varmt
    0.39
    lacion
    0.38
    tai
    0.38
     sodass
    0.38
    ⓧ
    0.38
    Pranala
    0.37
     scripted
    0.37
    amssymb
    0.37
     noastre
    0.37
    Activations Density 1.424%

    No Known Activations