© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9546
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, formulas, and related terms

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     يتيمه
    -0.79
    KommentareTeilen
    -0.63
     poveznice
    -0.62
     bezeichneter
    -0.60
    TagHelper
    -0.58
     صوتيه
    -0.58
     समीक्षाएं
    -0.57
    complexType
    -0.57
     nakalista
    -0.55
     Dernière
    -0.54
    POSITIVE LOGITS
     point
    0.62
     conditions
    0.58
    point
    0.57
     points
    0.56
     XCTest
    0.52
     Point
    0.52
    راتيج
    0.49
    points
    0.49
     عزیزم
    0.48
    liction
    0.48
    Activations Density 4.196%

    No Known Activations