© 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. 3059
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Mat" at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    Mat

    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
     utafitiHapana
    -0.95
     kasarigan
    -0.94
     propOrder
    -0.85
     Exacts
    -0.73
    IUrlHelper
    -0.73
    InvalidProtocol
    -0.73
     مشين
    -0.73
    IANGLES
    -0.72
    +#+#
    -0.72
     continúas
    -0.71
    POSITIVE LOGITS
    uri
    0.46
    ria
    0.42
    toni
    0.40
    isa
    0.38
    sub
    0.36
    čil
    0.36
    ua
    0.35
    neta
    0.34
    toc
    0.34
     traccia
    0.34
    Activations Density 1.008%

    No Known Activations