© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4559
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "ST" followed by the word "segment" or names that starts with "St"

    oai_token-act-pair · gemini-2.0-flash

    Medical tests/studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     hit
    -0.66
     hits
    -0.63
     Hit
    -0.62
     Hits
    -0.58
    Hit
    -0.56
    hits
    -0.54
    Hits
    -0.50
    AsUp
    -0.50
    hit
    -0.49
    ipedi
    -0.48
    POSITIVE LOGITS
     Saint
    1.03
    Saint
    0.95
     saint
    0.93
     Sankt
    0.88
    LookAnd
    0.87
     St
    0.80
     SAINT
    0.79
    Sainte
    0.77
    ankt
    0.74
    saint
    0.73
    Activations Density 0.371%

    No Known Activations