© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3051
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in "lly," sometimes along with words that come immediately before or after them.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     milhares
    -0.52
    Thousands
    -0.50
     thousands
    -0.50
     dólar
    -0.49
    thousands
    -0.49
     aDecoder
    -0.48
    nextLine
    -0.48
    ))[
    -0.48
     altrett
    -0.47
    HasIndex
    -0.47
    POSITIVE LOGITS
    ItemBackground
    0.92
     mergeFrom
    0.73
     Partly
    0.73
    Completely
    0.68
    Partly
    0.68
    Mostly
    0.65
     entirely
    0.63
    partly
    0.63
    Parti
    0.61
     Mostly
    0.61
    Activations Density 1.325%

    No Known Activations