© 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. 13371
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks surrounded by other words

    oai_token-act-pair · gemini-2.0-flash

    prefixes or beginnings of words

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

    Code/technical language

    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
    XmlAccessType
    -0.91
    httphttps
    -0.89
     getItemId
    -0.75
     Grecs
    -0.73
     femininos
    -0.73
    complexContent
    -0.71
     brancas
    -0.71
    awakeFromNib
    -0.70
    theless
    -0.69
     kasarigan
    -0.68
    POSITIVE LOGITS
    com
    0.63
    Jereo
    0.57
    ler
    0.56
    us
    0.55
    ষ্
    0.54
    ej
    0.54
    ･
    0.54
    الع
    0.54
    eria
    0.54
    es
    0.54
    Activations Density 12.177%

    No Known Activations