© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4293
    Prev
    Next
    INDEX
    Explanations

    language about politicians expressing a willingness to compromise and work together

    oai_token-act-pair · gemini-2.0-flash

    cooperation and collaboration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    chtete
    -0.61
    XtraReports
    -0.59
    Примітки
    -0.58
     EconPapers
    -0.57
     Normdatei
    -0.55
     Persi
    -0.54
    Geplaatst
    -0.52
    VIAF
    -0.52
     Answered
    -0.51
     plumage
    -0.49
    POSITIVE LOGITS
     cooperation
    1.13
     collaboration
    1.11
    Cooperation
    1.02
    cooperation
    1.01
    Collaboration
    0.98
     collaborations
    0.97
     collaborate
    0.97
    collaboration
    0.96
     colaboración
    0.94
     Collaboration
    0.92
    Activations Density 0.983%

    No Known Activations