© 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. 3912
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize importance or significance

    oai_token-act-pair · gemini-2.0-flash

    importance

    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
    ]<<"
    -0.49
     SUPPLIES
    -0.49
     constellations
    -0.47
     optik
    -0.47
     tramway
    -0.46
     Laplacian
    -0.46
     szóci
    -0.45
     useAppContext
    -0.45
    WriteLiteral
    -0.45
    akaian
    -0.45
    POSITIVE LOGITS
    ⓧ
    0.83
    posedge
    0.59
     estekak
    0.59
    кож
    0.57
    UpInside
    0.56
     indisponible
    0.56
    maksi
    0.55
     aDecoder
    0.54
    ocry
    0.54
    sodik
    0.54
    Activations Density 1.654%

    No Known Activations