© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8281
    Prev
    Next
    INDEX
    Explanations

    scientific articles, possibly figures or data, with some emphasis on "the"

    oai_token-act-pair · gemini-2.0-flash

    programming-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    More
    -0.54
    M
    -0.50
    S
    -0.48
    The
    -0.43
    un
    -0.43
    sp
    -0.43
    Time
    -0.42
    A
    -0.42
     More
    -0.41
    pr
    -0.40
    POSITIVE LOGITS
    ^(@)
    1.09
    RenderAtEndOf
    0.92
     AssemblyCulture
    0.90
    ^(@
    0.89
     Baillargeon
    0.87
     defaultstate
    0.86
     iſt
    0.83
     AssemblyTitle
    0.83
    featureID
    0.83
     greateſt
    0.82
    Activations Density 4.340%

    No Known Activations