© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9372
    Prev
    Next
    INDEX
    Explanations

    instances of indefinite articles followed by descriptive words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     quite
    -0.55
     considerable
    -0.54
     Huge
    -0.54
     aanzien
    -0.52
     Quite
    -0.52
     huge
    -0.51
    considerable
    -0.51
    onOptions
    -0.51
    lede
    -0.49
    //}
    -0.49
    POSITIVE LOGITS
    webElementXpaths
    0.76
    انيف
    0.66
     AssemblyVersion
    0.66
     propOrder
    0.66
    Personendaten
    0.62
    BeginContext
    0.61
    awtextra
    0.61
    InlineData
    0.61
    новништво
    0.59
    期刊论文
    0.59
    Activations Density 7.543%

    No Known Activations