© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3779
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands, especially those related to document structure and conditional statements.

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

    np_token-act-pair-logits · gpt-4o-mini

    LaTeX code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyTitle
    -0.55
     p
    -0.52
     u
    -0.52
     O
    -0.50
     E
    -0.50
     n
    -0.48
     ont
    -0.47
     ControllerBase
    -0.47
     o
    -0.46
     Q
    -0.45
    POSITIVE LOGITS
    InputBorder
    0.76
     فريبيس
    0.72
    Personendaten
    0.68
    enetrable
    0.67
    ndham
    0.67
    gether
    0.65
    ArgsConstructor
    0.63
    Jereo
    0.62
    Herkunft
    0.62
    WriteLiteral
    0.62
    Activations Density 2.516%

    No Known Activations