© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15081
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business reports

    oai_token-act-pair · gemini-2.0-flash

    the word "half"

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

    half

    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
     betweenstory
    -0.73
    RenderAtEndOf
    -0.70
    RegressionTest
    -0.66
     EconPapers
    -0.65
     Roskov
    -0.64
    CodedInputStream
    -0.64
     Paglinawan
    -0.60
    TargetException
    -0.57
    !*\
    -0.57
    InstanceState
    -0.56
    POSITIVE LOGITS
     half
    1.09
    half
    0.95
     Half
    0.90
    Half
    0.90
     lip
    0.84
    HALF
    0.82
     HALF
    0.80
     superficial
    0.78
     surface
    0.77
     token
    0.75
    Activations Density 5.343%

    No Known Activations