© 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. 10809
    Prev
    Next
    INDEX
    Explanations

    connectors and words related to belonging

    oai_token-act-pair · gemini-2.0-flash

    People

    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
     Mérimée
    -0.84
    xase
    -0.82
     ujednoznacz
    -0.82
    PreferredItem
    -0.79
     <=",
    -0.79
    parsedMessage
    -0.76
    SharedDtor
    -0.74
    astéroïdes
    -0.73
    RODUZIONE
    -0.72
    itinéraire
    -0.72
    POSITIVE LOGITS
     people
    0.98
     persons
    0.85
     players
    0.72
     individuals
    0.66
    people
    0.66
     folks
    0.65
     organisms
    0.64
     person
    0.62
     pessoas
    0.60
     entities
    0.58
    Activations Density 2.135%

    No Known Activations