© 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. 5841
    Prev
    Next
    INDEX
    Explanations

    the word "plan" or things related to planning and trips

    oai_token-act-pair · gemini-2.0-flash

    plan

    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
    utnik
    -0.59
     prêtres
    -0.59
    Editors
    -0.58
     juges
    -0.58
     Partagez
    -0.57
     dieux
    -0.57
     NavController
    -0.55
    idjan
    -0.55
     tanong
    -0.54
     estekak
    -0.54
    POSITIVE LOGITS
    ANTLR
    0.64
    참고
    0.57
     intptr
    0.50
     propOrder
    0.50
    //
    0.49
    تقاوى
    0.49
    off
    0.47
    namespace
    0.46
    存于互联网档案馆
    0.45
    OrBuilder
    0.45
    Activations Density 8.177%

    No Known Activations