© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 543
    Prev
    Next
    INDEX
    Explanations

    mathematical or physics equations or theorems or references

    oai_token-act-pair · gemini-2.0-flash

    math/physics theorems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    хьтан
    -0.67
     mergeFrom
    -0.66
    rungsseite
    -0.65
     AssemblyCulture
    -0.65
     @"/
    -0.63
    MigrationBuilder
    -0.63
     fieldNum
    -0.63
    OrBuilder
    -0.63
    TagMode
    -0.63
     Normdatei
    -0.62
    POSITIVE LOGITS
     Empirical
    0.56
     Progression
    0.54
     Cognition
    0.51
     Elasticity
    0.50
     Mortality
    0.48
     cavitation
    0.48
     Inequality
    0.48
     Polyn
    0.48
     Parametric
    0.46
    heimer
    0.46
    Activations Density 13.995%

    No Known Activations