© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6264
    Prev
    Next
    INDEX
    Explanations

    code blocks or conditional statements within code

    oai_token-act-pair · gemini-2.0-flash

    {

    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
    <bos>
    -2.47
    '
    -0.76
    ’
    -0.68
    I
    -0.56
    ‘
    -0.56
    2
    -0.55
    #
    -0.55
    ↵
    -0.54
    The
    -0.53
    Pro
    -0.52
    POSITIVE LOGITS
     protoimpl
    0.84
    ReusableCell
    0.78
    MemoryWarning
    0.78
     MotionEvent
    0.75
    :✨
    0.75
    parsedMessage
    0.73
     pinulongan
    0.73
    
    0.73
    IVEREF
    0.71
     AssemblyProduct
    0.70
    Activations Density 0.357%

    No Known Activations