© 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. 4617
    Prev
    Next
    INDEX
    Explanations

    LaTeX math formulas

    oai_token-act-pair · gemini-2.0-flash

    math

    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
    GHIJKLM
    -0.68
     endwhile
    -0.66
    InputBorder
    -0.62
    NOPQRST
    -0.62
    ScopeManager
    -0.59
    ValueStyle
    -0.58
    tinyos
    -0.57
     noDo
    -0.56
     Efq
    -0.56
     NCP
    -0.55
    POSITIVE LOGITS
     pauvres
    0.51
     élus
    0.50
     segar
    0.50
     penuh
    0.49
    expandindo
    0.48
     cavalli
    0.47
     nettoyer
    0.47
     merve
    0.47
     étudiants
    0.47
     sepen
    0.47
    Activations Density 6.659%

    No Known Activations