© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4477
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and acronyms, particularly those related to computer tech and biological science

    oai_token-act-pair · gemini-2.0-flash

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ंदीखरीदारी
    -0.96
     betweenstory
    -0.96
     distanciation
    -0.96
     ComVisible
    -0.94
     ――――――――
    -0.90
     practition
    -0.90
    potranspiration
    -0.86
     manufact
    -0.85
    Cordialement
    -0.82
    )";
    
    -0.82
    POSITIVE LOGITS
    wijs
    0.39
    <em>
    0.38
     L
    0.36
    водов
    0.36
     stessi
    0.36
    府
    0.36
    <b>
    0.36
    XtraGrid
    0.36
     Ma
    0.35
    란
    0.35
    Activations Density 10.135%

    No Known Activations