© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12535
    Prev
    Next
    INDEX
    Explanations

    words within mathematical or physics texts, especially related to stability and equilibrium

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    LEncoder
    -0.60
    departments
    -0.58
    ViewFeatures
    -0.56
    AnchorStyles
    -0.56
     teas
    -0.54
     hypot
    -0.54
    Sklici
    -0.54
    Gön
    -0.53
    +#+#
    -0.52
    urlpatterns
    -0.52
    POSITIVE LOGITS
    richTextPanel
    0.57
    memoized
    0.45
    akka
    0.45
    ശ
    0.43
    şak
    0.43
    面
    0.43
    #+#
    0.43
    oter
    0.42
     propOrder
    0.42
    sifs
    0.42
    Activations Density 5.955%

    No Known Activations