© 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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13728
    Prev
    Next
    INDEX
    Explanations

    mentions of the number 'one' used as a pronoun, adjective, or within a numbered list of items.

    oai_token-act-pair · gemini-2.0-flash

    one

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    mybatisplus
    -1.06
     Efq
    -1.05
     متعلقه
    -1.00
     ſche
    -0.95
     faſt
    -0.90
     ſever
    -0.90
     Chriftian
    -0.89
    oredCriteria
    -0.88
    PyExc
    -0.87
     Majefty
    -0.85
    POSITIVE LOGITS
    ,
    0.56
     for
    0.53
     in
    0.52
    .
    0.52
     is
    0.52
     from
    0.51
     as
    0.48
     and
    0.46
    const
    0.45
    st
    0.45
    Activations Density 5.900%

    No Known Activations