© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13708
    Prev
    Next
    INDEX
    Explanations

    various code characters, especially those used in math or coding notation

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     individuales
    -0.48
    individual
    -0.47
     ihren
    -0.45
    tir
    -0.44
     individuel
    -0.43
     she
    -0.43
     individual
    -0.42
     tố
    -0.41
    createElement
    -0.41
     CURLOPT
    -0.41
    POSITIVE LOGITS
     estekak
    0.96
    ManagedBean
    0.90
     nahilalakip
    0.85
    onViewCreated
    0.84
    ">//
    0.84
     mergeFrom
    0.82
     Paglinawan
    0.82
    AutoScaleMode
    0.77
    SpringBootTest
    0.74
    rungsseite
    0.74
    Activations Density 0.555%

    No Known Activations