© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9551
    Prev
    Next
    INDEX
    Explanations

    text from legal or institutional documents

    oai_token-act-pair · gemini-2.0-flash

    housing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     engage
    -1.87
     engaged
    -1.86
     engages
    -1.74
     engaging
    -1.65
     engagement
    -1.60
    engaged
    -1.60
     Engage
    -1.58
     Engaging
    -1.58
    Engage
    -1.57
    engage
    -1.55
    POSITIVE LOGITS
     housing
    1.84
     houses
    1.70
    housing
    1.61
     Housing
    1.53
    Housing
    1.48
     HOUSING
    1.44
     Houses
    1.37
    Houses
    1.31
    houses
    1.31
     house
    1.30
    Activations Density 6.662%

    No Known Activations