© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13403
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    -2.38
    To
    -2.22
     TO
    -1.24
    TO
    -0.93
    ToObject
    -0.79
    setTo
    -0.76
    ToLeft
    -0.74
    ToBe
    -0.74
    <bos>
    -0.70
    to
    -0.70
    POSITIVE LOGITS
    ImageContext
    0.85
     Infór
    0.78
    __*/
    0.77
    ReusableCell
    0.77
    makeConstraints
    0.73
    Rüyada
    0.71
    AnchorStyles
    0.69
    StoreMessageInfo
    0.68
    CloseOperation
    0.68
     Superhosts
    0.68
    Activations Density 1.254%

    No Known Activations