© 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. 9463
    Prev
    Next
    INDEX
    Explanations

    the word "continue" and its variants, along with seemingly random code

    oai_token-act-pair · gemini-2.0-flash

    continuous and ligand bonding

    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
     Italijanski
    -0.60
    írez
    -0.57
    ſelf
    -0.56
    risse
    -0.56
     JScrollPane
    -0.55
    MeasureSpec
    -0.55
     interpreter
    -0.54
    dike
    -0.54
     الرياضيه
    -0.54
    efel
    -0.54
    POSITIVE LOGITS
    expandindo
    0.65
    гин
    0.47
    outer
    0.46
    loys
    0.45
    Max
    0.44
    esterno
    0.43
    honest
    0.42
    U
    0.42
     puisse
    0.42
     thyme
    0.42
    Activations Density 0.539%

    No Known Activations