© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12107
    Prev
    Next
    INDEX
    Explanations

    the tokens "mat" and "Mat" in code or math contexts

    oai_token-act-pair · gemini-2.0-flash

    mat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     mat
    -2.61
    Mat
    -2.59
     Mat
    -2.53
    mat
    -2.45
    MAT
    -2.16
     MAT
    -2.11
    mats
    -1.86
     mats
    -1.84
     MATT
    -1.56
     matt
    -1.48
    POSITIVE LOGITS
     quedarse
    0.51
     idéia
    0.49
    чему
    0.48
    WarningLevel
    0.47
    ensement
    0.47
     bestäm
    0.46
    ări
    0.45
     manquer
    0.45
     comunicarse
    0.45
    HtmlAttribute
    0.44
    Activations Density 1.343%

    No Known Activations