© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12558
    Prev
    Next
    INDEX
    Explanations

    chemistry-related words and formulas referring to compounds with multiple connected components

    oai_token-act-pair · gemini-2.0-flash

    chemical formulas/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     StatefulWidget
    -0.52
    Notae
    -0.52
    styleable
    -0.51
    BagConstraints
    -0.50
    ệnh
    -0.50
    withIdentifier
    -0.48
    PerformLayout
    -0.48
    ](#
    -0.48
     noten
    -0.48
     jspb
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    0.64
     im
    0.60
     tả
    0.57
     Minaj
    0.54
    titial
    0.50
    retion
    0.49
     CURIAM
    0.49
    TestBed
    0.47
     py
    0.46
    şim
    0.46
    Activations Density 5.842%

    No Known Activations