© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5417
    Prev
    Next
    INDEX
    Explanations

    code excerpts, file operations including storage, and the word "can".

    oai_token-act-pair · gemini-2.0-flash

    storing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Aholisi
    -0.70
    adpleegd
    -0.57
    олові
    -0.52
    engarkan
    -0.52
    ंदीखरीदारी
    -0.51
    AnchorStyles
    -0.49
     personnalité
    -0.49
    runApp
    -0.49
     BorderSide
    -0.49
     MaterialApp
    -0.48
    POSITIVE LOGITS
     store
    0.68
     stock
    0.64
     Store
    0.62
    stock
    0.61
     stores
    0.57
     actionTypes
    0.56
    STO
    0.55
    IndentedString
    0.54
     sto
    0.54
    저
    0.53
    Activations Density 3.637%

    No Known Activations