© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9189
    Prev
    Next
    INDEX
    Explanations

    words ending in "s" within longer words, and sometimes other nearby words in the same sentence

    oai_token-act-pair · gemini-2.0-flash

    s

    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
     Wikimedijinoj
    -1.07
    Hochspringen
    -0.96
    ngdoc
    -0.91
     يتيمه
    -0.89
    seamnă
    -0.89
    檚
    -0.86
     Efq
    -0.85
    NameInMap
    -0.85
     CreateTagHelper
    -0.82
    writeField
    -0.82
    POSITIVE LOGITS
    <bos>
    1.23
    '
    0.77
    -
    0.62
    ’
    0.60
    "
    0.56
     I
    0.54
     
    0.54
    `
    0.52
    /
    0.52
    ↵
    0.52
    Activations Density 2.272%

    No Known Activations