© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    the word "to" appearing in various contexts

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming terminology

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

    interaction

    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
     to
    -0.63
     he
    -0.57
     To
    -0.50
     and
    -0.49
     I
    -0.48
     we
    -0.47
     
    -0.46
     do
    -0.46
     He
    -0.45
     they
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    1.27
    TagMode
    1.22
    InjectAttribute
    1.15
     purpoſe
    1.13
    RegressionTest
    1.06
    AddTagHelper
    1.02
     itſelf
    1.02
    Personendaten
    0.98
     uſed
    0.97
     pleaſure
    0.96
    Activations Density 4.267%

    No Known Activations