Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7067
    Prev
    Next
    INDEX
    Explanations

    the word "opportunity" as well as related words like "facility" and specific legal terms.

    oai_token-act-pair · gemini-2.0-flash

    opportunity

    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
    ,
    -0.70
    <bos>
    -0.63
    XmlEnum
    -0.54
    USDA
    -0.52
    Населення
    -0.52
    тистика
    -0.51
    —
    -0.51
    jLabel
    -0.50
     or
    -0.49
     continúas
    -0.49
    POSITIVE LOGITS
     pinulongan
    0.84
    ⓧ
    0.74
    MLLoader
    0.74
    }^{+\
    0.71
    ValueStyle
    0.71
     mijne
    0.69
     Lio
    0.69
     صوتيه
    0.69
     مشين
    0.68
     nonatomic
    0.68
    Activations Density 5.629%

    No Known Activations