© 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. 4876
    Prev
    Next
    INDEX
    Explanations

    words, symbols, and math notation in mathematical texts

    oai_token-act-pair · gemini-2.0-flash

    math proofs

    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
    Geplaatst
    -0.75
    ReusableCell
    -0.69
     cherchés
    -0.64
    providedIn
    -0.64
    enumii
    -0.64
    SharedCtor
    -0.60
     intptr
    -0.56
    :][
    -0.55
     PhpStorm
    -0.54
     sumpay
    -0.50
    POSITIVE LOGITS
     seams
    0.53
    jwa
    0.52
    protoimpl
    0.49
    loria
    0.47
    ніципа
    0.46
    突
    0.46
     subgroups
    0.46
    ZoneId
    0.46
    PROV
    0.45
     veze
    0.45
    Activations Density 17.789%

    No Known Activations