© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2134
    Prev
    Next
    INDEX
    Explanations

    U.S. cities, states, and other regions.

    oai_token-act-pair · gemini-2.0-flash

    US states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Texas
    -1.22
    Texas
    -1.20
     California
    -1.18
    California
    -1.18
     Florida
    -1.05
     Michigan
    -1.05
     Minnesota
    -1.05
    Florida
    -1.05
     Illinois
    -1.05
    Michigan
    -1.05
    POSITIVE LOGITS
    󠁢
    0.59
    ]--;
    0.58
    ])).
    0.56
    virons
    0.56
    oprecipitation
    0.52
    '])->
    0.51
    }))
    0.51
    '}>
    0.51
     Diwali
    0.50
    setContentView
    0.49
    Activations Density 5.003%

    No Known Activations