© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 97
    Prev
    Next
    INDEX
    Explanations

    words related to geography/location and their surrounding prepositions

    oai_token-act-pair · gemini-2.0-flash

    Locations

    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
    OGND
    -1.13
     Monfieur
    -1.04
     Efq
    -1.03
    tagHelperRunner
    -1.02
     defaultstate
    -1.02
    IsMutable
    -1.01
     ―――――
    -1.01
     propOrder
    -1.00
     initComponents
    -0.99
     GenerationType
    -0.98
    POSITIVE LOGITS
     Be
    0.53
     W
    0.51
    W
    0.51
     St
    0.51
     D
    0.51
     Con
    0.50
    ↵
    0.50
     H
    0.50
     New
    0.50
    D
    0.49
    Activations Density 1.392%

    No Known Activations