© 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. 14442
    Prev
    Next
    INDEX
    Explanations

    the word "to" and words preceding "to" with some association

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating actionable choices or opportunities

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

    to

    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
    -0.88
     actuelles
    -0.62
     extérieures
    -0.60
     médicaux
    -0.58
     actuels
    -0.57
     supérieures
    -0.54
     kepada
    -0.54
     exceptionnelle
    -0.53
     storici
    -0.52
     médicale
    -0.51
    POSITIVE LOGITS
     spend
    0.85
     qualify
    0.84
     participate
    0.82
     deliver
    0.82
     autorytatywna
    0.81
     settle
    0.81
     execute
    0.80
     germinate
    0.80
     incorporate
    0.80
     communicate
    0.79
    Activations Density 3.044%

    No Known Activations