© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11373
    Prev
    Next
    INDEX
    Explanations

    sequences from scientific documents describing chemical properties and their measurements

    oai_token-act-pair · gemini-2.0-flash

    formulas and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    istle
    -0.55
    ssa
    -0.53
    المناصب
    -0.50
    errcode
    -0.47
     march
    -0.45
     BorderSide
    -0.44
    cess
    -0.42
     pur
    -0.41
     περ
    -0.41
    march
    -0.40
    POSITIVE LOGITS
    Personensuche
    0.65
     esterni
    0.64
    bleau
    0.60
    ыгана
    0.60
    CloseOperation
    0.59
     ostavi
    0.59
    LookAnd
    0.59
    ParallelGroup
    0.58
     invokingState
    0.58
    BagConstraints
    0.57
    Activations Density 0.587%

    No Known Activations