© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4921
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode formatting

    oai_token-act-pair · gemini-2.0-flash

    mk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ">//
    -0.75
    itinéraire
    -0.67
    Personensuche
    -0.66
    RectangleBorder
    -0.66
     estekak
    -0.66
     lenker
    -0.65
     kasarigan
    -0.64
    省市镇
    -0.64
    новниш
    -0.64
     postIndex
    -0.63
    POSITIVE LOGITS
    openSession
    0.49
    orElseThrow
    0.46
    </strong>
    0.45
    Tokenizer
    0.45
     Workshop
    0.45
    webElement
    0.45
    arise
    0.45
    udio
    0.45
     Office
    0.45
    ristan
    0.44
    Activations Density 63.878%

    No Known Activations