© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15468
    Prev
    Next
    INDEX
    Explanations

    single letters or short letter sequences, especially those that appear to be errors or parts of chemical structures or acronyms.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    LookAnd
    -0.75
    MigrationBuilder
    -0.73
     protoimpl
    -0.73
    astéroïdes
    -0.71
     <<<<<<<<<<<<<<
    -0.71
     <=",
    -0.70
    hematical
    -0.67
    BibitemShut
    -0.66
    gnition
    -0.66
    .}(
    -0.65
    POSITIVE LOGITS
    s
    0.53
     scattata
    0.50
     prisa
    0.49
     sidor
    0.49
     înc
    0.46
     täh
    0.45
     particulières
    0.45
     modalités
    0.44
     arada
    0.44
    dır
    0.44
    Activations Density 3.825%

    No Known Activations