© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10029
    Prev
    Next
    INDEX
    Explanations

    the word "item", particularly within code snippets

    oai_token-act-pair · gemini-2.0-flash

    item

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     item
    -2.34
     Item
    -2.28
    Item
    -2.09
     items
    -2.05
     Items
    -1.98
    item
    -1.92
     ITEM
    -1.90
    items
    -1.73
    ITEM
    -1.70
     ITEMS
    -1.68
    POSITIVE LOGITS
     braccio
    0.56
     MutableLiveData
    0.53
    แน่น
    0.51
     MessageBoxIcon
    0.49
    jsxFileName
    0.49
    
    0.48
    setPreferred
    0.48
     enne
    0.47
    Fag
    0.47
     CURI
    0.47
    Activations Density 2.236%

    No Known Activations