© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3354
    Prev
    Next
    INDEX
    Explanations

    recipes

    oai_token-act-pair · gemini-2.0-flash

    whisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ItemBackground
    -0.48
    <thead>
    -0.41
    Are
    -0.40
    дости
    -0.36
    SY
    -0.35
    We
    -0.35
    才
    -0.34
    are
    -0.33
     libera
    -0.33
     Are
    -0.32
    POSITIVE LOGITS
    tagHelperRunner
    0.89
    LookAnd
    0.81
    .*")]
    0.77
    enumi
    0.72
    Geplaatst
    0.71
     تضيفلها
    0.71
    Hentet
    0.70
    ftagPool
    0.67
     uintptr
    0.67
     HttpServlet
    0.66
    Activations Density 0.474%

    No Known Activations