© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11251
    Prev
    Next
    INDEX
    Explanations

    new stories by detecting locations and/or law enforcement

    oai_token-act-pair · gemini-2.0-flash

    deputies

    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
     propOrder
    -0.68
    featureID
    -0.58
     AssemblyTitle
    -0.56
     >=",
    -0.55
    Билгалдахарш
    -0.53
    ([...
    -0.50
    (!__
    -0.49
    Personensuche
    -0.49
    értelmű
    -0.48
    jusi
    -0.47
    POSITIVE LOGITS
    gameserver
    0.60
     nacht
    0.56
     Ngb
    0.54
     ویکی‌پدیای
    0.53
    MessageState
    0.48
    éreo
    0.48
     morning
    0.47
     gece
    0.47
    RunAsync
    0.46
    Fuß
    0.46
    Activations Density 1.002%

    No Known Activations