© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5423
    Prev
    Next
    INDEX
    Explanations

    words that are misspelled or have unusual character combinations

    oai_token-act-pair · gemini-2.0-flash

    programming terms and technical conditions

    np_token-act-pair-logits · gpt-4o-mini

    programming and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    expandindo
    -0.96
    ReusableCell
    -0.93
    `;
    
    -0.80
    ValueStyle
    -0.78
    `,
    
    -0.76
     Wiktionnaire
    -0.74
    FTFY
    -0.71
     متعلقه
    -0.71
     ligiloj
    -0.71
    ]`
    -0.69
    POSITIVE LOGITS
    temp
    0.52
    ‌است
    0.52
    use
    0.51
    byt
    0.49
    jspx
    0.49
    printStackTrace
    0.49
    <bos>
    0.47
    fun
    0.46
    up
    0.46
    ISTA
    0.46
    Activations Density 6.363%

    No Known Activations