© 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. 4706
    Prev
    Next
    INDEX
    Explanations

    location and transportation-related terms (addresses, stations, roads, apartments, automobiles or descriptions of movement between locations)

    oai_token-act-pair · gemini-2.0-flash

    stairs and elevators

    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
     <=",
    -0.62
     >=",
    -0.56
     TestBed
    -0.54
    Gemeinsame
    -0.54
     garage
    -0.52
     garages
    -0.52
    forName
    -0.50
    abetes
    -0.50
    lunda
    -0.48
     сю
    -0.47
    POSITIVE LOGITS
    contentLoaded
    0.66
     elevator
    0.55
    AnimationsModule
    0.55
    stair
    0.54
    XtraBars
    0.52
     elevators
    0.52
     intptr
    0.52
     STAM
    0.52
     stair
    0.50
     staircase
    0.50
    Activations Density 0.723%

    No Known Activations