© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6928
    Prev
    Next
    INDEX
    Explanations

    occurrences of "we" followed by verbs indicating analysis

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     our
    -0.53
     We
    -0.53
     ourselves
    -0.52
     we
    -0.51
    We
    -0.47
    我們
    -0.47
    是我们
    -0.46
     nostro
    -0.43
    讓我們
    -0.42
     WE
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.94
    存于互联网档案馆
    0.86
    Vidite
    0.71
    المناصب
    0.71
     arşivlendi
    0.70
    AddTagHelper
    0.69
    AddHtmlAttribute
    0.69
     Bioaccumulative
    0.66
    AndEndTag
    0.66
     initComponents
    0.66
    Activations Density 4.112%

    No Known Activations