© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8773
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate uncertainty, questions, or commands

    oai_token-act-pair · 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
    writeFieldEnd
    -0.59
    appcompat
    -0.57
    ">—
    -0.49
     romantique
    -0.49
     Puoi
    -0.49
    SpringBootTest
    -0.48
     appelez
    -0.48
     Monfieur
    -0.47
     jaka
    -0.47
     näm
    -0.46
    POSITIVE LOGITS
     ComVisible
    0.60
     مشين
    0.57
    JpaRepository
    0.54
    cotta
    0.54
    lineEdit
    0.53
    mingen
    0.50
    PECT
    0.49
    eadilan
    0.48
    çais
    0.48
     utafitiHapana
    0.48
    Activations Density 0.748%

    No Known Activations