© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4211
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially percentages, values with decimal points, or values with units

    oai_token-act-pair · gemini-2.0-flash

    Numerical digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ⓧ
    -0.94
    Tikang
    -0.79
     BorderRadius
    -0.74
    WaitGroup
    -0.74
     Signalez
    -0.73
    Personensuche
    -0.68
    CloseOperation
    -0.68
    sizeCache
    -0.67
     ContentValues
    -0.66
    GEBURTSDATUM
    -0.65
    POSITIVE LOGITS
    োগ
    0.45
     cliquant
    0.43
     jih
    0.43
    ^@
    0.42
     سخت
    0.41
    listFiles
    0.41
     favorable
    0.40
    dania
    0.40
     Benton
    0.40
    sess
    0.40
    Activations Density 4.764%

    No Known Activations