© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15160
    Prev
    Next
    INDEX
    Explanations

    text involving numerical comparisons and math symbols

    oai_token-act-pair · gemini-2.0-flash

    mathematical terms

    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
     ostavi
    -0.68
    AnimationsModule
    -0.66
    consulté
    -0.66
    endphp
    -0.57
     AssemblyTitle
    -0.57
    ConstraintMaker
    -0.56
     FetchType
    -0.54
    ISupport
    -0.53
     domés
    -0.53
     >=",
    -0.53
    POSITIVE LOGITS
     fractions
    0.68
     quadratic
    0.67
     Fractions
    0.67
     probability
    0.66
     trig
    0.62
    probability
    0.61
     quadril
    0.60
    quadratic
    0.60
     Quadratic
    0.60
     quadrat
    0.60
    Activations Density 9.306%

    No Known Activations