© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10951
    Prev
    Next
    INDEX
    Explanations

    words ending in "sed" or "sise," usually variants on "size."

    oai_token-act-pair · gemini-2.0-flash

    sed

    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
    TemporalType
    -0.71
    keyColumn
    -0.71
    ImageContext
    -0.67
     getItemId
    -0.67
     newBuilder
    -0.66
    InstrumentedTest
    -0.64
     getRule
    -0.61
     INTERESAR
    -0.56
     Anson
    -0.55
    ($__
    -0.55
    POSITIVE LOGITS
    isation
    0.83
    ising
    0.76
    izing
    0.75
    isations
    0.74
    tisation
    0.73
    ization
    0.72
    lize
    0.71
    IZING
    0.71
    alisation
    0.71
     hoá
    0.68
    Activations Density 0.247%

    No Known Activations