© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6350
    Prev
    Next
    INDEX
    Explanations

    a plus/minus sign surrounded by numbers, with or without additional context like 'years' or 'points'.

    oai_token-act-pair · gemini-2.0-flash

    Plus-minus symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     présidentielle
    -0.47
    AsUp
    -0.46
    InstanceState
    -0.46
    ddling
    -0.46
     Mars
    -0.46
    léans
    -0.44
    mbol
    -0.44
    udt
    -0.43
    ën
    -0.42
    endphp
    -0.42
    POSITIVE LOGITS
     StatefulWidget
    0.76
     MessageBoxIcon
    0.70
     الرياضيه
    0.69
     ſtate
    0.68
    TagMode
    0.67
    unnitel
    0.67
     Monfieur
    0.66
    ۇ
    0.64
    CloseOperation
    0.63
    basicConfig
    0.63
    Activations Density 0.920%

    No Known Activations