© 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. 10465
    Prev
    Next
    INDEX
    Explanations

    some form of a quantity, either an adjective describing a noun, or a noun modifying something with a measurement.

    oai_token-act-pair · gemini-2.0-flash

    rest/remainder

    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
    ’
    -0.58
    ↵
    -0.50
    '
    -0.48
    ↵↵
    -0.48
     No
    -0.42
    kjø
    -0.42
    بوابة
    -0.42
     own
    -0.42
     EdgeInsets
    -0.41
     la
    -0.41
    POSITIVE LOGITS
    queryInterface
    0.93
    DockStyle
    0.89
    ValueStyle
    0.83
    EndContext
    0.82
     AssemblyProduct
    0.81
    AddTagHelper
    0.81
    URLException
    0.81
    UserScript
    0.80
    antMatchers
    0.79
    DeleteBehavior
    0.78
    Activations Density 1.184%

    No Known Activations