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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8567
    Prev
    Next
    INDEX
    Explanations

    LaTeX math expressions

    oai_token-act-pair · gemini-2.0-flash

    Latex/Math symbols

    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
    rawn
    -0.53
     gourd
    -0.47
    ECH
    -0.47
    \
    -0.46
    Jeb
    -0.46
    ).__
    -0.45
     stead
    -0.45
    Geografi
    -0.44
    Symfony
    -0.44
    NI
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.73
     MainAxisSize
    0.62
     محفوظة
    0.60
     protoimpl
    0.60
     propOrder
    0.58
    isContained
    0.55
     vectorielles
    0.54
     vectoriales
    0.54
     auroit
    0.53
    LayoutStyle
    0.52
    Activations Density 2.004%

    No Known Activations