© 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. 5533
    Prev
    Next
    INDEX
    Explanations

    the word "reason."

    oai_token-act-pair · gemini-2.0-flash

    reason

    np_max-act · 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
     BoxFit
    -0.73
    XmlRootElement
    -0.68
    itemBuilder
    -0.66
    enterOuterAlt
    -0.65
    addContainerGap
    -0.63
    rawDesc
    -0.61
    <bos>
    -0.61
    :+:
    -0.60
    CGRectMake
    -0.60
    ManagedBean
    -0.60
    POSITIVE LOGITS
    プリング
    0.46
    Collecting
    0.45
    паль
    0.45
     Desai
    0.44
    ไหน
    0.44
     beweg
    0.44
    লি
    0.43
     spark
    0.43
    EndProject
    0.43
     Alfaro
    0.43
    Activations Density 1.029%

    No Known Activations