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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12023
    Prev
    Next
    INDEX
    Explanations

    instructions or directions within technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Computing and system administration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     disambiguazione
    -1.00
    MigrationBuilder
    -1.00
     Мексичка
    -0.94
     myſelf
    -0.94
     Efq
    -0.93
    reportWebVitals
    -0.93
    AsUp
    -0.92
     setInterval
    -0.92
    脚注の使い方
    -0.90
    PreferredItem
    -0.90
    POSITIVE LOGITS
     “
    0.43
     "
    0.42
    オー
    0.42
     //
    0.41
    OR
    0.41
    RY
    0.38
     ‘
    0.38
     penge
    0.37
    <eos>
    0.37
    te
    0.36
    Activations Density 0.614%

    No Known Activations