© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5857
    Prev
    Next
    INDEX
    Explanations

    conjunctions and discourse markers that set up conditional statements, questions and quotations.

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    يكب
    -0.52
    ttino
    -0.46
     चाहिए
    -0.46
    󠁢
    -0.44
     beginnetje
    -0.44
     padx
    -0.43
     Picchu
    -0.43
     useHistory
    -0.43
     Kreise
    -0.42
    issauga
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.64
     newBuilder
    0.59
     kasarigan
    0.57
    cookieParser
    0.55
     zvuky
    0.55
     BorderRadius
    0.54
    gulation
    0.54
    Tikang
    0.54
     numberOfRows
    0.54
     cauſe
    0.52
    Activations Density 0.728%

    No Known Activations