© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10866
    Prev
    Next
    INDEX
    Explanations

    real estate ads and accounting service descriptions.

    oai_token-act-pair · gemini-2.0-flash

    starting

    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
    وصلات
    -0.47
    getvalue
    -0.45
    timeout
    -0.44
    DriverManager
    -0.42
     kasarigan
    -0.42
     jury
    -0.41
    YTE
    -0.41
     AttributeSet
    -0.40
    requireNonNull
    -0.40
    setupUi
    -0.39
    POSITIVE LOGITS
     starting
    2.39
     Starting
    2.22
    Starting
    2.17
    starting
    2.17
     starts
    2.13
     start
    2.00
     Starts
    1.97
     STARTING
    1.91
    starts
    1.81
    start
    1.78
    Activations Density 1.847%

    No Known Activations