© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11971
    Prev
    Next
    INDEX
    Explanations

    words and phrases about prison, jail, and the legal system

    oai_token-act-pair · gemini-2.0-flash

    Prison and custody

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     prisonniers
    -0.69
     ویکی‌پدیا
    -0.65
     الرياضيه
    -0.64
    Prison
    -0.62
     pinulongan
    -0.59
     réfugiés
    -0.59
     PRISON
    -0.58
     Prison
    -0.58
    bootstrapcdn
    -0.57
     démocr
    -0.56
    POSITIVE LOGITS
     beat
    0.52
    geslacht
    0.49
     Lau
    0.48
    허
    0.47
    isole
    0.47
    IEWS
    0.47
    gway
    0.46
    BrowserModule
    0.46
     справи
    0.46
     Super
    0.45
    Activations Density 2.275%

    No Known Activations