© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14007
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing emotional distress or hardship

    oai_token-act-pair · gemini-2.0-flash

    negative/restricted situations

    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
    rawler
    -0.50
     ter
    -0.47
    cerin
    -0.46
    PutMapping
    -0.43
    づき
    -0.43
    IMENT
    -0.43
     <>",
    -0.42
    shadowOpacity
    -0.42
     adet
    -0.42
    ureusement
    -0.42
    POSITIVE LOGITS
    AnchorStyles
    0.77
    GEBURTSDATUM
    0.72
    ftagPool
    0.71
    ConstraintMaker
    0.67
    StructEnd
    0.66
    InputBorder
    0.65
    RectangleBorder
    0.60
    Искәрмәләр
    0.60
     ویکی‌پدیای
    0.59
    setVerticalGroup
    0.58
    Activations Density 5.630%

    No Known Activations