© 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. 10639
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and variable assignments.

    oai_token-act-pair · gemini-2.0-flash

    technical/code texts

    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
     comigo
    -0.61
     militaires
    -0.56
     aéri
    -0.50
     bonté
    -0.47
     quæ
    -0.47
    mappedBy
    -0.47
     spagno
    -0.47
    tangentMode
    -0.47
     cùng
    -0.47
     marinho
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.61
    FunctionFlags
    0.61
    SPJ
    0.60
     للتو
    0.60
    ɵɵ
    0.58
    toHaveBeen
    0.56
    twimg
    0.56
    StylePriority
    0.55
     ostavi
    0.55
    TagMode
    0.55
    Activations Density 2.299%

    No Known Activations