© 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. 9607
    Prev
    Next
    INDEX
    Explanations

    references to Ohio and legal entities.

    oai_token-act-pair · gemini-2.0-flash

    location names

    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
     pinulongan
    -0.88
     mergeFrom
    -0.74
     esternos
    -0.71
     كومونز
    -0.70
    DoubleQuotes
    -0.68
     otomatig
    -0.68
    enumi
    -0.65
     Wiktionnaire
    -0.64
     cherchés
    -0.61
    parsedMessage
    -0.61
    POSITIVE LOGITS
     banques
    0.48
    CHESTER
    0.47
     Jérusalem
    0.46
    Poland
    0.44
     indipendente
    0.44
     vechi
    0.41
     Caledonia
    0.41
     ainfi
    0.41
    Arkansas
    0.40
     Köl
    0.40
    Activations Density 0.547%

    No Known Activations