© 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. 3297
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on words relating to frontiers and borders, as well as time.

    oai_token-act-pair · gemini-2.0-flash

    deadlines and timers

    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
     AssemblyTitle
    -0.70
    NUMX
    -0.66
    memoized
    -0.66
     unmute
    -0.66
     TextInputType
    -0.65
     caricature
    -0.64
     محفوظة
    -0.64
    DoubleQuotes
    -0.63
    RegressionTest
    -0.63
     XNUMX
    -0.62
    POSITIVE LOGITS
    TagMode
    0.46
    idious
    0.42
     Pflanze
    0.42
     pouvoirs
    0.41
     начало
    0.41
    tometer
    0.41
    zeiger
    0.41
     internal
    0.41
     перемен
    0.40
     her
    0.40
    Activations Density 1.661%

    No Known Activations