© 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. 14759
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to websites as well as language about health

    oai_token-act-pair · gemini-2.0-flash

    Website/general advice

    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
     Krakowie
    -0.50
     dourado
    -0.43
    toon
    -0.42
     če
    -0.42
    “
    -0.39
    tock
    -0.39
    Online
    -0.39
    線上
    -0.38
    ksikon
    -0.37
     unknownFields
    -0.37
    POSITIVE LOGITS
    WriteBarrier
    0.72
    ]")]
    0.71
    Xna
    0.69
    PyExc
    0.65
    gwt
    0.65
    تقاوى
    0.65
     <>",
    0.62
    RetentionPolicy
    0.59
     становника
    0.56
    MessageState
    0.56
    Activations Density 1.920%

    No Known Activations