© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5818
    Prev
    Next
    INDEX
    Explanations

    references to Amendments or legal discourse.

    oai_token-act-pair · gemini-2.0-flash

    legal and political texts

    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
     First
    -1.88
     Second
    -1.79
     Three
    -1.76
     Third
    -1.74
     Fourth
    -1.70
     Two
    -1.61
     Four
    -1.59
    First
    -1.58
     Five
    -1.57
     Fifth
    -1.57
    POSITIVE LOGITS
     disambiguazione
    0.60
    Cyfeiriadau
    0.56
    Искәрмәләр
    0.54
    AccessorTable
    0.50
     Utili
    0.46
    Viitteet
    0.46
    GenerationType
    0.46
     Lifestyle
    0.45
     lenker
    0.44
    Neces
    0.43
    Activations Density 8.021%

    No Known Activations