© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9989
    Prev
    Next
    INDEX
    Explanations

    words that are simply common, and show up frequently in normal writing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     المعيارى
    -0.57
     zelfs
    -0.53
    ม้
    -0.53
    にも
    -0.51
     ddelweddau
    -0.50
    ckså
    -0.50
    gså
    -0.49
    ValueStyle
    -0.48
    webElementXpaths
    -0.48
    日閲覧
    -0.47
    POSITIVE LOGITS
    ########.
    0.62
     StatelessWidget
    0.57
    Rather
    0.56
    GEBURTSDATUM
    0.56
     Rather
    0.55
    instead
    0.55
    Instead
    0.54
     rather
    0.54
    あく
    0.54
     instead
    0.54
    Activations Density 15.735%

    No Known Activations