© 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. 7868
    Prev
    Next
    INDEX
    Explanations

    code snippets containing test assertions and environment variable handling in Javascript/Typescript

    oai_token-act-pair · gemini-2.0-flash

    expect

    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
     or
    -0.65
    mer
    -0.63
    ies
    -0.62
    ob
    -0.62
    pro
    -0.62
    us
    -0.62
     the
    -0.60
    '
    -0.60
    ,
    -0.60
    und
    -0.59
    POSITIVE LOGITS
     Мексичка
    1.11
     crdi
    1.06
     Monfieur
    1.04
     fathoms
    1.03
     Cæsar
    1.02
     myſelf
    1.02
     photolibrary
    1.02
     piaggio
    1.00
     plufieurs
    1.00
     feroit
    0.98
    Activations Density 2.160%

    No Known Activations