© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8776
    Prev
    Next
    INDEX
    Explanations

    the letter 'd' likely when it's following a space or apostrophe

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     d
    -1.22
    UrlResolution
    -0.69
    SequentialGroup
    -0.69
    ніципа
    -0.67
     Administrativna
    -0.64
     متعلقه
    -0.63
     يتيمه
    -0.59
     виправивши
    -0.57
    GEBURTSDATUM
    -0.56
    uncher
    -0.55
    POSITIVE LOGITS
    日閲覧
    0.61
    "]];
    0.57
    ---|---|
    0.57
    (_,
    0.56
    /')
    0.53
    \",\"
    0.50
    /")
    0.50
    ']]
    0.49
     发表于
    0.49
    ](#
    0.49
    Activations Density 0.980%

    No Known Activations