© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11508
    Prev
    Next
    INDEX
    Explanations

    text related to legal rights and claims

    oai_token-act-pair · gemini-2.0-flash

    laws and rights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    RenderAtEndOf
    -0.66
     doInBackground
    -0.61
     MonoBehaviour
    -0.56
    Espèce
    -0.52
     MatDialog
    -0.48
    蜒
    -0.48
    ventude
    -0.47
    GraphicsUnit
    -0.47
     BrowserModule
    -0.47
    PRNewswire
    -0.47
    POSITIVE LOGITS
     laws
    0.81
     rights
    0.79
     Rights
    0.75
     RIGHTS
    0.74
     law
    0.73
     statute
    0.73
     Constitutional
    0.71
     constitutional
    0.69
     Laws
    0.69
     legality
    0.69
    Activations Density 4.394%

    No Known Activations