© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5496
    Prev
    Next
    INDEX
    Explanations

    words related to scientific publications discussing experiments and data analysis

    oai_token-act-pair · gemini-2.0-flash

    calculation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    windowFixed
    -0.54
     betweenstory
    -0.54
    AddTagHelper
    -0.52
    WithIOException
    -0.51
    |')
    -0.48
    }>{
    -0.46
     forState
    -0.45
    sonic
    -0.45
     Gat
    -0.45
     jsPsych
    -0.44
    POSITIVE LOGITS
     calculations
    1.20
     modeling
    1.20
     calculation
    1.16
     modelling
    1.14
     simulations
    1.13
     models
    1.08
    Calculations
    1.07
    calculations
    1.06
     mathematical
    1.05
     calcul
    1.05
    Activations Density 11.242%

    No Known Activations