© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10982
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the former US President Donald Trump and his administration, sometimes abbreviated as DDT.

    oai_token-act-pair · gemini-2.0-flash

    brief

    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
     ReactDOM
    -0.52
    揄
    -0.52
    umask
    -0.50
    cycline
    -0.49
    olol
    -0.48
    Glej
    -0.46
     Meld
    -0.44
    يميديا
    -0.44
    rimos
    -0.43
     Lecture
    -0.42
    POSITIVE LOGITS
     brief
    2.63
     Brief
    2.14
    brief
    1.98
    Brief
    1.95
     BRIEF
    1.88
    BRIEF
    1.38
     briefly
    1.30
     briefs
    1.29
     Briefs
    1.13
     brie
    1.11
    Activations Density 3.259%

    No Known Activations