© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4910
    Prev
    Next
    INDEX
    Explanations

    phrases that include numbers (especially numbers indicating floors or sizes of properties) and the words relating to buildings and locations

    oai_token-act-pair · gemini-2.0-flash

    Homes and buildings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    tagHelperRunner
    -0.69
     House
    -0.63
    tvguidetime
    -0.60
     kasarigan
    -0.59
    House
    -0.59
    TestTools
    -0.58
    }`).
    -0.58
     HOUSE
    -0.57
    XmlAccessType
    -0.56
     Houses
    -0.55
    POSITIVE LOGITS
    converted
    0.58
     conversions
    0.57
     conversion
    0.55
    conversion
    0.53
     converted
    0.50
     Grade
    0.50
     disambiguazione
    0.48
    ="'+
    0.48
     Mosquito
    0.48
     perpetuity
    0.48
    Activations Density 0.997%

    No Known Activations