© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6696
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business, economy, finance, and healthcare, like "clients", "benefits", "clinical", "consultant".

    oai_token-act-pair · gemini-2.0-flash

    business and clients

    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
    <bos>
    -1.46
    toHaveBeen
    -0.57
    bors
    -0.51
     Afterward
    -0.51
    Geplaatst
    -0.50
    #
    -0.50
     BnF
    -0.50
     ögon
    -0.49
     Recognize
    -0.48
    insics
    -0.47
    POSITIVE LOGITS
     مشين
    0.82
     שוליים
    0.75
     lenker
    0.63
     فريبيس
    0.59
    منابع
    0.56
    erals
    0.54
    tamol
    0.54
    ReusableCell
    0.53
    InputBorder
    0.51
    DriverManager
    0.50
    Activations Density 1.816%

    No Known Activations