© 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. 12912
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings and religious deities

    oai_token-act-pair · gemini-2.0-flash

    Legal/religious texts

    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
    \{\\
    -0.84
    findpost
    -0.79
     onCancelled
    -0.65
    }{*}{
    -0.64
     []).
    -0.63
    
    -0.61
    httphttps
    -0.58
    apimachinery
    -0.56
    出版年
    -0.56
    Geplaatst
    -0.56
    POSITIVE LOGITS
     This
    0.50
     There
    0.48
     They
    0.48
     Another
    0.48
     Offisielt
    0.48
     Some
    0.46
     Their
    0.45
     These
    0.44
     CURIAM
    0.44
     You
    0.44
    Activations Density 7.570%

    No Known Activations