© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10608
    Prev
    Next
    INDEX
    Explanations

    the phrase "as opposed to"

    oai_token-act-pair · gemini-2.0-flash

    opposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     المعيارى
    -0.72
    CppMethod
    -0.71
    RegressionTest
    -0.71
     numberOfRows
    -0.69
    DebuggerNonUser
    -0.68
     RouterModule
    -0.68
    featureID
    -0.66
    AndEndTag
    -0.66
    Hochspringen
    -0.66
    Parcelize
    -0.66
    POSITIVE LOGITS
     mại
    0.49
    cheinend
    0.45
     نهایت
    0.45
    хах
    0.44
    としても
    0.43
     passaggio
    0.43
    としては
    0.42
    FunctionFlags
    0.42
    offsetTop
    0.42
     moral
    0.41
    Activations Density 0.909%

    No Known Activations