© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2171
    Prev
    Next
    INDEX
    Explanations

    parts of addresses

    oai_token-act-pair · gemini-2.0-flash

    Addresses and locations

    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
     ProtoMessage
    -0.62
     betweenstory
    -0.58
    protoimpl
    -0.58
    bitat
    -0.55
    aarrggbb
    -0.54
    doh
    -0.53
    RegressionTest
    -0.52
     aDecoder
    -0.52
    postsleuth
    -0.51
    ########.
    -0.49
    POSITIVE LOGITS
     street
    0.84
     streets
    0.68
    streets
    0.67
     Street
    0.66
    STREET
    0.66
    Street
    0.66
     STREET
    0.63
    street
    0.63
     ули
    0.60
    Streets
    0.59
    Activations Density 0.295%

    No Known Activations