© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11683
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and related concepts, along with related discussions about right and wrong

    oai_token-act-pair · gemini-2.0-flash

    trigonometry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     sin
    -1.69
     Sin
    -1.66
    Sin
    -1.63
     SIN
    -1.54
    sin
    -1.52
     sins
    -1.28
    SIN
    -1.27
     cos
    -1.26
     Sins
    -1.24
     Sine
    -1.23
    POSITIVE LOGITS
    onChanged
    0.44
    contentLoaded
    0.38
     flechas
    0.38
    stoel
    0.38
    vieja
    0.36
     przew
    0.36
    NameInMap
    0.36
     rivi
    0.35
    ح
    0.35
     lại
    0.34
    Activations Density 1.067%

    No Known Activations