© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 192
    Prev
    Next
    INDEX
    Explanations

    the word "it" being used in technical documents and legal disclaimers

    oai_token-act-pair · gemini-2.0-flash

    "It 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Jurí
    -0.50
     uzupeł
    -0.49
     Histórico
    -0.48
     Universitaria
    -0.47
     StringTokenizer
    -0.47
    InitVars
    -0.47
     greateſt
    -0.46
     anhyd
    -0.45
    uszcz
    -0.45
    stanbul
    -0.45
    POSITIVE LOGITS
     Is
    2.31
     Has
    2.16
    Is
    2.03
    Has
    2.03
     Will
    1.89
     Does
    1.78
    Will
    1.77
     Was
    1.70
    Does
    1.66
     Can
    1.57
    Activations Density 11.727%

    No Known Activations