© 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. 951
    Prev
    Next
    INDEX
    Explanations

    mentions of something not happening until a certain point in time

    oai_token-act-pair · gemini-2.0-flash

    until

    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
    ministerium
    -0.49
     elector
    -0.48
    agus
    -0.47
     táctil
    -0.47
    DJANGO
    -0.46
    ameters
    -0.44
    rikes
    -0.43
    OwnProperty
    -0.43
     electors
    -0.42
    IVEREF
    -0.42
    POSITIVE LOGITS
    <bos>
    1.02
     незавершена
    0.57
     kasarigan
    0.57
     يتيمه
    0.56
    SequentialGroup
    0.54
     once
    0.50
     विश्वसनीयता
    0.50
    URLException
    0.50
     köln
    0.49
     članak
    0.49
    Activations Density 1.506%

    No Known Activations