© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6556
    Prev
    Next
    INDEX
    Explanations

    code-like or code-related tokens in a document

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    setVerticalGroup
    -0.79
    SBATCH
    -0.65
    ISupport
    -0.55
    initComponents
    -0.55
    ViewFeatures
    -0.54
    antMatchers
    -0.54
     EnglishChoose
    -0.53
    getActiveSheet
    -0.52
     незавершена
    -0.52
     مشين
    -0.50
    POSITIVE LOGITS
    جار
    0.48
    พาะ
    0.45
    OfBirth
    0.45
    Życiorys
    0.44
    DataPropertyName
    0.43
    ======
    0.43
     Excise
    0.43
    zeera
    0.42
    hoea
    0.42
     excise
    0.42
    Activations Density 0.272%

    No Known Activations