© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5471
    Prev
    Next
    INDEX
    Explanations

    mentions of courts, laws, acts, government bodies, and legal processes

    oai_token-act-pair · gemini-2.0-flash

    Act or Law

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    bró
    -0.50
    AccessorTable
    -0.47
    BRO
    -0.46
    enumi
    -0.42
     Hause
    -0.42
    ContextHolder
    -0.41
    core
    -0.41
     menyer
    -0.41
    (/^
    -0.41
     consultato
    -0.40
    POSITIVE LOGITS
    rrggbb
    0.75
     Roskov
    0.70
    IUrlHelper
    0.60
     CreateTagHelper
    0.59
     grants
    0.59
     Hatfield
    0.59
    eradish
    0.59
     Hano
    0.58
    NUMX
    0.57
    🏻‍♀️
    0.57
    Activations Density 6.627%

    No Known Activations