© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12144
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to theoretical physics and symmetries in physics

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ChromeDriver
    -0.66
    enumii
    -0.63
     nakalista
    -0.63
     OnInit
    -0.63
    endfor
    -0.60
     utafitiHapana
    -0.60
     ProtoMessage
    -0.60
     '\\;'
    -0.59
     consultato
    -0.56
    Formik
    -0.56
    POSITIVE LOGITS
     internetowa
    0.48
     unbroken
    0.45
    chero
    0.44
    زب
    0.42
    ourites
    0.42
    BRON
    0.42
    BREAK
    0.41
     BREAK
    0.41
     نق
    0.41
     prie
    0.40
    Activations Density 1.421%

    No Known Activations