© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4593
    Prev
    Next
    INDEX
    Explanations

    LaTeX math delimiters and symbols, particularly those related to norms, variables, and equations.

    oai_token-act-pair · gemini-2.0-flash

    math equations and proofs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     $|
    -1.41
    |
    -1.40
    =|
    -1.40
     $|\
    -1.34
    $|
    -1.32
    |\
    -1.26
    |'
    -1.23
    |"
    -1.22
    |$
    -1.20
    }|
    -1.20
    POSITIVE LOGITS
    Билгалдахарш
    0.49
    exitRule
    0.47
    iprot
    0.44
    Descripció
    0.41
    ValueStyle
    0.41
     MenuView
    0.41
     LIABLE
    0.38
    WithIOException
    0.38
    Życiorys
    0.37
     समीक्षाओं
    0.37
    Activations Density 1.164%

    No Known Activations