© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9839
    Prev
    Next
    INDEX
    Explanations

    statistical studies

    oai_token-act-pair · gemini-2.0-flash

    research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     يتيمه
    -0.58
    parsedMessage
    -0.57
     Administrativna
    -0.50
     useHistory
    -0.50
    DoubleQuotes
    -0.49
    Salta
    -0.48
     فريبيس
    -0.48
    UrlResolution
    -0.48
    apatan
    -0.47
    expandindo
    -0.46
    POSITIVE LOGITS
     Sharing
    0.58
    SequentialGroup
    0.56
     سكانية
    0.55
    oneph
    0.52
    Sharing
    0.51
    ViewImports
    0.51
    ildes
    0.50
     shares
    0.50
    ními
    0.50
     sharing
    0.50
    Activations Density 13.426%

    No Known Activations