© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8180
    Prev
    Next
    INDEX
    Explanations

    time-related words, especially days of the week and adjectives

    oai_token-act-pair · gemini-2.0-flash

    days of week

    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
    <bos>
    -1.79
     الحره
    -1.20
     تضيفلها
    -0.81
    Personensuche
    -0.81
     Мексичка
    -0.77
     INTERESAR
    -0.75
    quelize
    -0.73
     BoxFit
    -0.73
    MemoryWarning
    -0.72
    rrggbb
    -0.72
    POSITIVE LOGITS
     cr
    0.49
    colate
    0.49
     greatest
    0.48
    greatest
    0.46
     kind
    0.46
     Erne
    0.46
     how
    0.45
     Weg
    0.44
    igre
    0.44
     culpa
    0.44
    Activations Density 0.348%

    No Known Activations