© 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. 11970
    Prev
    Next
    INDEX
    Explanations

    mathematical language, especially theorems, lemmas, and equations.

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     hâte
    -0.91
     supérieurs
    -0.90
     étroite
    -0.90
    IsMutable
    -0.88
     صوتيه
    -0.87
     normaux
    -0.85
     positifs
    -0.84
     initComponents
    -0.84
    windowFixed
    -0.83
    RegistryLite
    -0.82
    POSITIVE LOGITS
     ver
    0.43
     (
    0.43
     rec
    0.42
     ra
    0.42
     di
    0.41
     prec
    0.40
    é
    0.40
    se
    0.40
     st
    0.40
    fl
    0.40
    Activations Density 6.707%

    No Known Activations