© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4763
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "are."

    oai_token-act-pair · gemini-2.0-flash

    Are

    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
     I
    -1.42
    I
    -1.27
     i
    -0.96
    ฉัน
    -0.70
    i
    -0.70
     я
    -0.69
    我
    -0.67
    Ｉ
    -0.66
     Tôi
    -0.59
    我都
    -0.57
    POSITIVE LOGITS
     GetEnumerator
    0.96
     you
    0.85
     <=",
    0.83
    AnimationsModule
    0.81
     مشين
    0.81
    ImageContext
    0.71
     متعلقه
    0.69
    ThroughAttribute
    0.69
     indisponible
    0.68
     saites
    0.68
    Activations Density 0.687%

    No Known Activations