© 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. 12951
    Prev
    Next
    INDEX
    Explanations

    the word "to" near 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
     zelve
    -0.63
    setViewportView
    -0.63
     дописавши
    -0.62
    ReusableCell
    -0.60
    Портали
    -0.60
     ſeveral
    -0.59
     myſelf
    -0.59
    GIH
    -0.56
    azgo
    -0.56
     étoit
    -0.56
    POSITIVE LOGITS
    <bos>
    0.70
     يتيمه
    0.64
     turn
    0.61
     مواليد
    0.55
     focus
    0.51
     turns
    0.51
    '
    0.50
    uerre
    0.49
    ństwa
    0.49
    turn
    0.48
    Activations Density 0.172%

    No Known Activations