© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6573
    Prev
    Next
    INDEX
    Explanations

    words related to expressing personal opinions or directives

    oai_token-act-pair · gemini-2.0-flash

    presence of the word "is"

    np_token-act-pair-logits · gpt-4o-mini

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ConstraintMaker
    -0.73
    تقاوى
    -0.69
     الحره
    -0.63
    RectangleBorder
    -0.63
    InjectAttribute
    -0.63
     EconPapers
    -0.62
    IUrlHelper
    -0.57
    CodedInputStream
    -0.57
    KommentareTeilen
    -0.52
    siers
    -0.52
    POSITIVE LOGITS
     is
    1.99
     Is
    1.27
    Is
    1.11
    is
    0.96
     are
    0.85
    的是
    0.84
     IS
    0.84
     adalah
    0.83
     là
    0.81
     است
    0.80
    Activations Density 4.294%

    No Known Activations