© 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
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 13035
    Prev
    Next
    INDEX
    Explanations

    words indicating some kind of problem

    oai_token-act-pair · gemini-2.0-flash

    negative phrasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     gabbana
    -0.69
    -------------</
    -0.62
    \{\\
    -0.60
    cete
    -0.59
    disha
    -0.59
     урна
    -0.57
    awić
    -0.56
    bourhood
    -0.56
    smarty
    -0.56
    ständige
    -0.55
    POSITIVE LOGITS
    msgTypes
    0.61
    енча
    0.53
    RRect
    0.48
    AdapterView
    0.48
    InstrumentedTest
    0.46
     Momb
    0.45
     Hath
    0.44
    AddHtmlAttribute
    0.44
    CodeAttribute
    0.44
     nahilalakip
    0.43
    Activations Density 3.119%

    No Known Activations