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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6230
    Prev
    Next
    INDEX
    Explanations

    the prefix "mon", likely referring to the beginning of words like monomial, monocyte, or monolith

    oai_token-act-pair · gemini-2.0-flash

    mon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     mon
    -1.11
    Manbalar
    -0.98
     Мексичка
    -0.91
     Mon
    -0.88
    ##
    -0.77
     متعلقه
    -0.77
     okuyayım
    -0.71
    atalos
    -0.71
    Mon
    -0.71
    mon
    -0.70
    POSITIVE LOGITS
    loven
    0.55
    '
    0.55
    Chham
    0.54
     arada
    0.54
    Tikang
    0.52
     democrática
    0.52
     lieto
    0.51
    The
    0.51
    n
    0.51
     comerciais
    0.50
    Activations Density 0.351%

    No Known Activations