© 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. 11068
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments defining piecewise functions

    oai_token-act-pair · gemini-2.0-flash

    equations

    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
     '\\;'
    -0.75
    ConstraintMaker
    -0.72
    setContentView
    -0.72
    WaitGroup
    -0.69
     anſ
    -0.64
     fubject
    -0.63
     ſtate
    -0.61
    LayoutConstraint
    -0.60
     poffe
    -0.57
     JpaRepository
    -0.57
    POSITIVE LOGITS
    FERENCE
    0.57
    ListItem
    0.52
     propOrder
    0.52
    ombic
    0.51
    bolista
    0.50
    пати
    0.50
    urses
    0.50
    nolia
    0.49
    sitis
    0.49
    sizable
    0.48
    Activations Density 0.064%

    No Known Activations