© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    instances of international cooperation in an official or government context

    oai_token-act-pair · gemini-2.0-flash

    Locations and Agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    expandindo
    -0.65
    rungsseite
    -0.62
    tagHelperRunner
    -0.61
    elemField
    -0.60
    ConstraintMaker
    -0.58
    oneofs
    -0.56
    bitField
    -0.56
     disponibilités
    -0.54
    mergeFrom
    -0.54
     fieldNum
    -0.54
    POSITIVE LOGITS
     Malaysia
    0.56
    vamos
    0.56
    uncios
    0.55
    óngase
    0.54
     Kazakhstan
    0.53
     Maladies
    0.52
     dac
    0.52
     Silla
    0.52
     Ea
    0.51
     GLUT
    0.51
    Activations Density 8.225%

    No Known Activations