© 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. 6330
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "ed", past tense verbs and other suffixes.

    oai_token-act-pair · 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
    :✨
    -0.72
    ComponentScan
    -0.63
     &___
    -0.62
     <>",
    -0.62
     للتو
    -0.60
     gobier
    -0.60
    elsa
    -0.57
    ②
    -0.54
    rungsseite
    -0.53
     citoy
    -0.53
    POSITIVE LOGITS
     to
    0.88
    InputTagHelper
    0.79
    ergies
    0.76
     LCCN
    0.75
    ensitivity
    0.69
    tamount
    0.69
    ipment
    0.66
    clonal
    0.66
     sensitivity
    0.65
    koneksi
    0.65
    Activations Density 3.757%

    No Known Activations