© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6709
    Prev
    Next
    INDEX
    Explanations

    mentions of towns and cities

    oai_token-act-pair · gemini-2.0-flash

    references to cities or towns

    np_token-act-pair-logits · gpt-4o-mini

    city or town

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    DropTable
    -0.68
    SharedDtor
    -0.61
    BufferException
    -0.57
     }));
    -0.54
    buttonBar
    -0.54
     betweenstory
    -0.53
     ddelweddau
    -0.51
     Normdatei
    -0.49
    featureID
    -0.48
    principalColumn
    -0.48
    POSITIVE LOGITS
     city
    2.31
     town
    2.13
     City
    1.95
    city
    1.89
    City
    1.81
     CITY
    1.77
     cities
    1.71
     Town
    1.67
    CITY
    1.65
     TOWN
    1.59
    Activations Density 1.908%

    No Known Activations