© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12210
    Prev
    Next
    INDEX
    Explanations

    US and European addresses, especially postal codes

    oai_token-act-pair · gemini-2.0-flash

    postal codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    TypedDataSet
    -0.68
    principalTable
    -0.66
    principalColumn
    -0.64
    ]")]
    -0.60
     JpaRepository
    -0.58
    __((
    -0.58
    __()
    -0.54
    WaitGroup
    -0.54
     kiện
    -0.52
    featureID
    -0.52
    POSITIVE LOGITS
    guém
    0.52
     /#
    0.49
    خبار
    0.48
     pinulongan
    0.48
     Homme
    0.45
    IMDG
    0.45
     Theſe
    0.45
    hamshire
    0.44
     जाने
    0.44
    ipot
    0.42
    Activations Density 0.276%

    No Known Activations