© 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. 11461
    Prev
    Next
    INDEX
    Explanations

    mentions of towns, regions, and provinces in countries

    oai_token-act-pair · 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
     гипер
    -0.40
     sports
    -0.39
    guisement
    -0.38
    λέον
    -0.38
    Civi
    -0.37
     medication
    -0.37
     Uribe
    -0.37
     Medication
    -0.36
     intentional
    -0.36
     magist
    -0.36
    POSITIVE LOGITS
     pinulongan
    0.78
    Manbalar
    0.73
    GraphicsUnit
    0.67
    textAppearance
    0.67
    HasForeignKey
    0.67
    saraba
    0.66
    urator
    0.66
     Roskov
    0.66
    extAlignment
    0.66
    ArrowToggle
    0.66
    Activations Density 1.187%

    No Known Activations