© 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. 10975
    Prev
    Next
    INDEX
    Explanations

    html code dealing with column sizing

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · 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
     שוליים
    -0.63
     StatefulWidget
    -0.60
    verwijspagina
    -0.58
     المعيارى
    -0.57
    utilisons
    -0.50
    ัฒนา
    -0.49
     snippetHide
    -0.49
     Signalez
    -0.48
    AndFlush
    -0.47
    يكب
    -0.47
    POSITIVE LOGITS
    fromString
    0.50
    offsetWidth
    0.48
    newBuilder
    0.48
     الاطلاع
    0.47
    jetty
    0.46
    otipo
    0.46
     FetchType
    0.46
    ucket
    0.45
    nloa
    0.45
    SharedCtor
    0.45
    Activations Density 0.093%

    No Known Activations