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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11643
    Prev
    Next
    INDEX
    Explanations

    words associated with data tables, reporting, and retail commerce

    oai_token-act-pair · gemini-2.0-flash

    User interfaces or systems

    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
     صوتيه
    -0.71
     Houſe
    -0.66
     doubtnut
    -0.66
    ussis
    -0.66
    HomeAsUp
    -0.63
     ་་
    -0.62
     Exo
    -0.61
     ARXIV
    -0.61
     Brahmin
    -0.60
    LElement
    -0.59
    POSITIVE LOGITS
    <bos>
    0.76
    Vanjske
    0.45
     affich
    0.44
     
    0.44
     despe
    0.44
    しく
    0.42
    <code>
    0.41
    Identyfik
    0.41
     secar
    0.41
     presidencial
    0.40
    Activations Density 4.167%

    No Known Activations