© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8769
    Prev
    Next
    INDEX
    Explanations

    sentences that describe the reason or purpose for something

    oai_token-act-pair · gemini-2.0-flash

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    PerformLayout
    -0.77
    WriteTagHelper
    -0.75
    NameInMap
    -0.69
    SourceChecksum
    -0.65
    ûn
    -0.60
     OMITBAD
    -0.59
    ($__
    -0.59
    SequentialGroup
    -0.56
    chowa
    -0.56
    UnusedPrivate
    -0.55
    POSITIVE LOGITS
    MemoryWarning
    0.56
     hoping
    0.56
     because
    0.52
     omdat
    0.52
     để
    0.52
    Because
    0.52
     Hoping
    0.51
    dropIfExists
    0.50
     permettra
    0.49
    __':
    0.49
    Activations Density 1.626%

    No Known Activations