© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5783
    Prev
    Next
    INDEX
    Explanations

    code snippets, based on keywords such as "style", "item", database related terms, and "AttributeSet"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     myſelf
    -2.02
     Efq
    -1.77
     itſelf
    -1.75
     Monfieur
    -1.65
     Houſe
    -1.63
     ―――――
    -1.59
    ſelf
    -1.57
     Jefus
    -1.56
     Majefty
    -1.55
     pleaſure
    -1.54
    POSITIVE LOGITS
     
    1.07
     [
    0.91
     The
    0.85
     )
    0.84
     (
    0.82
     "
    0.81
     <
    0.80
     *
    0.80
     -
    0.79
     E
    0.76
    Activations Density 16.909%

    No Known Activations