© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11146
    Prev
    Next
    INDEX
    Explanations

    words related to buildings and property, especially dimensions and modifications

    oai_token-act-pair · gemini-2.0-flash

    Locations, buildings, plans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     estekak
    -0.65
     saites
    -0.52
     judiciales
    -0.50
    archiviato
    -0.50
    CODES
    -0.49
     Scripts
    -0.49
    phous
    -0.49
    setViewportView
    -0.49
    WEBPACK
    -0.48
     deadlock
    -0.48
    POSITIVE LOGITS
     WPS
    0.56
     Italijanski
    0.53
     >",
    0.53
    IBarButtonItem
    0.51
     AssemblyCulture
    0.51
    CBM
    0.49
     sicher
    0.47
     MCI
    0.46
     vermic
    0.45
     kitchen
    0.45
    Activations Density 1.420%

    No Known Activations