© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10161
    Prev
    Next
    INDEX
    Explanations

    references to principles, standards, and laws

    oai_token-act-pair · gemini-2.0-flash

    principle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    WebElementEntity
    -0.65
    }$​
    -0.63
    principles
    -0.60
     PRINCIPLES
    -0.58
    expandindo
    -0.58
     intestines
    -0.57
     guts
    -0.56
     елның
    -0.56
    laws
    -0.56
     GIPHY
    -0.55
    POSITIVE LOGITS
    SourceChecksum
    0.65
     initComponents
    0.59
    ibouti
    0.56
    AddTagHelper
    0.54
     viewDidLoad
    0.54
    
    0.53
    duto
    0.52
    glBegin
    0.52
    toBeTruthy
    0.51
    stoß
    0.51
    Activations Density 1.467%

    No Known Activations