© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3607
    Prev
    Next
    INDEX
    Explanations

    words related to electric potential and circuits

    oai_token-act-pair · gemini-2.0-flash

    voltage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mergeFrom
    -0.59
     للاسماء
    -0.59
    mmate
    -0.59
    raquo
    -0.54
    ьаж
    -0.54
     blz
    -0.53
    Cyfeiriadau
    -0.52
    __((
    -0.51
    таратура
    -0.50
    IsTrue
    -0.50
    POSITIVE LOGITS
     voltage
    1.02
     Voltage
    0.94
     voltages
    0.89
     volts
    0.86
    Voltage
    0.83
    voltage
    0.81
     VOLTAGE
    0.80
     voltaje
    0.77
     Volts
    0.77
     V
    0.75
    Activations Density 1.659%

    No Known Activations