© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11092
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions like sine and cosine

    oai_token-act-pair · gemini-2.0-flash

    sin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     sine
    -0.78
     Sine
    -0.74
    sine
    -0.73
    Réalisation
    -0.71
    DockStyle
    -0.71
     sin
    -0.71
    rénées
    -0.68
    Sine
    -0.66
     trigonometric
    -0.65
     Sinus
    -0.61
    POSITIVE LOGITS
     cell
    0.79
    cell
    0.73
    CELL
    0.73
     cells
    0.69
     Cell
    0.65
    Cell
    0.64
     CELL
    0.63
     Zellen
    0.58
    MLLoader
    0.57
    cells
    0.56
    Activations Density 0.477%

    No Known Activations