© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10857
    Prev
    Next
    INDEX
    Explanations

    text related to foreign policy and international relations, particularly those involving Morocco.

    oai_token-act-pair · gemini-2.0-flash

    politics/history/culture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    StoryboardSegue
    -0.65
    XmlAccessorType
    -0.60
    OrNil
    -0.57
    BufferException
    -0.56
     propOrder
    -0.55
     disposizione
    -0.55
     commerciale
    -0.54
    IUrlHelper
    -0.54
     StatelessWidget
    -0.54
    gameserver
    -0.53
    POSITIVE LOGITS
    mtx
    0.48
     SwitchCompat
    0.45
    userdetails
    0.45
    lodge
    0.44
    rawDesc
    0.44
    ServiceModel
    0.43
    ITCHEN
    0.43
    اشت
    0.43
    adaptiveStyles
    0.43
    ALSO
    0.42
    Activations Density 0.560%

    No Known Activations