© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7632
    Prev
    Next
    INDEX
    Explanations

    HTML line breaks

    oai_token-act-pair · gemini-2.0-flash

    br

    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
    br
    -1.69
     br
    -1.27
    Br
    -1.18
    BR
    -1.10
     Br
    -1.04
     BR
    -0.86
    BRC
    -0.71
    brd
    -0.65
    brando
    -0.62
    bró
    -0.62
    POSITIVE LOGITS
    AndEndTag
    0.94
    setVerticalGroup
    0.71
     arşivlendi
    0.70
    IBarButtonItem
    0.65
    ClientRect
    0.61
    potranspiration
    0.61
    Superview
    0.60
    avimo
    0.60
    TagMode
    0.59
    ThroughAttribute
    0.59
    Activations Density 0.169%

    No Known Activations