© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8125
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and notation in scientific documents

    oai_token-act-pair · gemini-2.0-flash

    Math symbols

    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
     where
    -1.74
    where
    -1.60
    Where
    -1.50
     Where
    -1.48
     donde
    -1.34
     où
    -1.23
     WHERE
    -1.21
    WHERE
    -1.16
     где
    -1.15
    donde
    -1.13
    POSITIVE LOGITS
     protoimpl
    0.97
     Efq
    0.91
    oa̍t
    0.88
    kloped
    0.86
    igshid
    0.85
    EndContext
    0.84
    TagHelper
    0.81
     createSlice
    0.79
     InputDecoration
    0.79
    OGND
    0.79
    Activations Density 5.761%

    No Known Activations