© 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. 10516
    Prev
    Next
    INDEX
    Explanations

    code snippets with the words "add" or "remove"

    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_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
    add
    -1.03
     Add
    -0.85
    Add
    -0.80
     add
    -0.79
    ADD
    -0.72
    HasKey
    -0.60
     ADD
    -0.60
     Adding
    -0.58
    ToAdd
    -0.58
    adding
    -0.57
    POSITIVE LOGITS
    MethodManager
    0.66
    SequentialGroup
    0.65
    ⓧ
    0.64
    فایل‌لار
    0.56
     незавершена
    0.56
    HtmlAttribute
    0.56
     مرئيه
    0.54
    nodoc
    0.54
    setVerticalGroup
    0.53
    EndContext
    0.53
    Activations Density 0.184%

    No Known Activations