© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    words related to either sports or medical treatment

    oai_token-act-pair · gemini-2.0-flash

    championships; returning to normal

    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
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.77
    DeleteBehavior
    -0.75
     ब्रेकडाउन
    -0.74
     NSCoder
    -0.72
    MessageOf
    -0.71
     المعيارى
    -0.71
     Pristupljeno
    -0.69
    )}</
    -0.69
    ExecuteReader
    -0.68
    })`
    -0.68
    POSITIVE LOGITS
     campaign
    0.61
     Campaign
    0.54
     campagne
    0.52
     CAMPAIGN
    0.47
    Campaign
    0.47
     campagna
    0.45
     campaigns
    0.45
     neighbour
    0.43
     arc
    0.42
    ifen
    0.42
    Activations Density 1.704%

    No Known Activations