© 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. 5884
    Prev
    Next
    INDEX
    Explanations

    text from academic papers and mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Physics and math equations

    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
     iprot
    -0.52
    contentLoaded
    -0.52
    Попис
    -0.51
     CascadeType
    -0.51
    droje
    -0.51
    PerformLayout
    -0.50
    fxml
    -0.49
     propOrder
    -0.49
    存于互联网档案馆
    -0.47
    ArrowToggle
    -0.47
    POSITIVE LOGITS
    expandindo
    0.67
    SourceChecksum
    0.65
    ynomial
    0.58
    Kontrola
    0.56
    lgari
    0.54
     Wick
    0.53
     EClass
    0.53
    +#+
    0.53
     eins
    0.53
    ər
    0.52
    Activations Density 6.895%

    No Known Activations