© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    sentences about historical societies and collections of artifacts and documents.

    oai_token-act-pair · gemini-2.0-flash

    Museum, collections, historical artifacts

    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
    ("")]
    -0.50
     jewel
    -0.49
    viewDidLoad
    -0.47
    amssymb
    -0.46
    Geplaatst
    -0.45
     counter
    -0.45
    IContainer
    -0.45
    findpost
    -0.45
    BufferException
    -0.44
     Amu
    -0.44
    POSITIVE LOGITS
     AssemblyVersion
    0.60
     me
    0.56
    ellemző
    0.54
    omitempty
    0.52
    aibo
    0.51
    RegressionTest
    0.51
     remplacé
    0.51
    UnusedPrivate
    0.50
     satunya
    0.49
     rn
    0.49
    Activations Density 8.716%

    No Known Activations