© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10507
    Prev
    Next
    INDEX
    Explanations

    C-style code comments with asterisks and forward slashes

    oai_token-act-pair · gemini-2.0-flash

    code comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AndEndTag
    -0.75
     snippetHide
    -0.72
     CreateTagHelper
    -0.67
    
    -0.65
     ThemeData
    -0.65
    OrBuilder
    -0.62
     initComponents
    -0.62
    NameInMap
    -0.58
    ValueStyle
    -0.56
     الرياضيه
    -0.56
    POSITIVE LOGITS
     Problem
    0.51
    <tbody>
    0.50
     Test
    0.50
    \
    0.50
     Motion
    0.49
     Solution
    0.48
     Ball
    0.48
     j
    0.48
     Public
    0.47
     The
    0.47
    Activations Density 24.361%

    No Known Activations