© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14197
    Prev
    Next
    INDEX
    Explanations

    Java code that adds items to lists, sets, or tabbed panes, especially including the word "add" itself

    oai_token-act-pair · gemini-2.0-flash

    add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    add
    -1.18
    Add
    -1.03
     Add
    -0.96
     add
    -0.90
    ADD
    -0.79
     ADD
    -0.71
     adds
    -0.68
     adding
    -0.66
    Adding
    -0.62
     Adds
    -0.62
    POSITIVE LOGITS
    \{\\
    0.77
    Бахар
    0.71
     StatefulWidget
    0.70
    stdc
    0.68
    rungsseite
    0.68
    πάν
    0.67
    SBATCH
    0.65
    SourceChecksum
    0.65
    izoen
    0.63
    iconque
    0.63
    Activations Density 3.262%

    No Known Activations