© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15118
    Prev
    Next
    INDEX
    Explanations

    numbers in code samples or numerical data

    oai_token-act-pair · gemini-2.0-flash

    code and data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    awtextra
    -0.49
    are
    -0.47
    τερα
    -0.46
    Bind
    -0.46
    Хьажоргаш
    -0.46
    ures
    -0.45
    alm
    -0.45
    ter
    -0.43
    IDA
    -0.43
    ché
    -0.43
    POSITIVE LOGITS
    ,
    0.79
    ///</
    0.65
    WebControls
    0.58
     marinho
    0.57
     Мексичка
    0.57
    出版年
    0.56
     ProductService
    0.55
     magique
    0.54
     secondaire
    0.53
    DebuggerStep
    0.53
    Activations Density 4.354%

    No Known Activations