© 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. 10460
    Prev
    Next
    INDEX
    Explanations

    words that relate to daily tasks and abstract concepts that are part of discussions or arguments

    oai_token-act-pair · 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
     calldata
    -0.55
    AddTagHelper
    -0.54
     Expédié
    -0.53
    >{@
    -0.52
     дописавши
    -0.52
    setDo
    -0.51
    riculum
    -0.50
    IndentedString
    -0.50
    typeparam
    -0.49
    unto
    -0.49
    POSITIVE LOGITS
     intptr
    0.67
    enapa
    0.58
    MemoryWarning
    0.56
    ExecuteReader
    0.56
    GetAxis
    0.55
    printStackTrace
    0.54
     ThemeData
    0.52
    bewerken
    0.52
    новништво
    0.52
     Washing
    0.52
    Activations Density 2.832%

    No Known Activations