© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12043
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs with "down", "out", "into" or "up".

    oai_token-act-pair · gemini-2.0-flash

    down/out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.54
    HasForeignKey
    -0.51
    transQ
    -0.50
     quit
    -0.48
     Quit
    -0.47
    望
    -0.45
    ísimas
    -0.44
     stopp
    -0.43
     fieldNum
    -0.43
     tố
    -0.43
    POSITIVE LOGITS
    ientôt
    0.77
     percolation
    0.64
    XtraReports
    0.61
    gwick
    0.60
    icordia
    0.59
     Wirth
    0.59
     klink
    0.58
    olera
    0.58
    tableFuture
    0.56
     препратки
    0.56
    Activations Density 0.369%

    No Known Activations