© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12832
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions that often appear in legal and academic writing.

    oai_token-act-pair · gemini-2.0-flash

    In

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AdapterView
    -0.61
    IBOutlet
    -0.57
    #+#
    -0.56
    дям
    -0.55
    দ্ধ
    -0.53
     Dioxide
    -0.53
    ("}");
    -0.52
    FailureListener
    -0.52
     IBOutlet
    -0.52
    getClassLoader
    -0.52
    POSITIVE LOGITS
     kasarigan
    0.69
     يتيمه
    0.60
     transfieras
    0.59
     pinulongan
    0.58
    enschappelijke
    0.56
    Примітки
    0.54
    Примечания
    0.54
     AssemblyCulture
    0.53
     препратки
    0.52
     تانيه
    0.52
    Activations Density 1.608%

    No Known Activations