© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12338
    Prev
    Next
    INDEX
    Explanations

    C data structures with 64-bit integer variables

    oai_token-act-pair · gemini-2.0-flash

    Underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    _
    -0.88
     restTemplate
    -0.55
    \_
    -0.55
    ByDefault
    -0.52
    onoma
    -0.52
    DataMember
    -0.51
     Verses
    -0.50
     MonoBehaviour
    -0.50
    ẠI
    -0.50
     hemis
    -0.49
    POSITIVE LOGITS
    <bos>
    1.02
    GenerationType
    0.70
    IsContent
    0.65
    клопе
    0.65
    >');
    0.60
    ')));
    0.60
    >`;
    0.59
    ")),
    0.59
    ']],
    0.59
    '))
    0.57
    Activations Density 5.573%

    No Known Activations