© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8087
    Prev
    Next
    INDEX
    Explanations

    code syntax like database calls, object properties, access modifiers

    oai_token-act-pair · gemini-2.0-flash

    db

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.10
     estekak
    -0.82
     فريبيس
    -0.79
    原始内容存档于
    -0.78
     חיצוניים
    -0.75
    ValueStyle
    -0.75
    存于互联网档案馆
    -0.74
    ItemBackground
    -0.74
    __':
    -0.73
     Administrativna
    -0.68
    POSITIVE LOGITS
    woff
    0.59
     above
    0.56
     Humble
    0.51
    LayoutConstraint
    0.49
    pulumi
    0.49
    itemId
    0.49
     Amino
    0.48
    iq
    0.48
    slf
    0.48
     amino
    0.47
    Activations Density 0.314%

    No Known Activations