© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    references to religious events and locations, especially Catholic.

    oai_token-act-pair · gemini-2.0-flash

    Public events

    np_max-act · gemini-2.0-flash

    events

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     AssemblyProduct
    -0.77
    ConstraintMaker
    -0.73
    setVerticalGroup
    -0.72
    awaiter
    -0.68
    المناصب
    -0.67
    
    -0.67
    SOUNDBITE
    -0.66
     chande
    -0.65
    tagext
    -0.63
    licone
    -0.63
    POSITIVE LOGITS
    <bos>
    0.46
     ↑
    0.46
    </b>
    0.45
     paio
    0.44
     rahasia
    0.44
    хо
    0.42
    .
    0.42
    ,
    0.40
    ign
    0.40
    [
    0.40
    Activations Density 3.671%

    No Known Activations