© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3619
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to commerce, shipping, applications, and legal documents, with a focus on conditions, exceptions, and specifications.

    oai_token-act-pair · gemini-2.0-flash

    say

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ReusableCell
    -0.66
    webElementXpaths
    -0.60
    qtt
    -0.53
    RenderAtEndOf
    -0.52
    NOPQRST
    -0.50
    ftagPool
    -0.50
     typelib
    -0.48
     Carroll
    -0.48
    readFileSync
    -0.46
     onBind
    -0.46
    POSITIVE LOGITS
     says
    1.01
     say
    0.96
     stated
    0.91
     indicate
    0.89
     stating
    0.88
    says
    0.88
     indicated
    0.87
    Says
    0.87
     lists
    0.86
     saying
    0.84
    Activations Density 2.266%

    No Known Activations