© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6440
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to economics, trade, and shipping, as well as general transportation.

    oai_token-act-pair · gemini-2.0-flash

    words related to being trapped or stuck

    np_token-act-pair-logits · gpt-4o-mini

    trapped stuck

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    pielt
    -0.49
    etsy
    -0.44
     Coloque
    -0.42
     kain
    -0.42
     förr
    -0.40
    awtextra
    -0.39
     nullptr
    -0.39
    ступили
    -0.39
     indoss
    -0.39
     Drapeau
    -0.39
    POSITIVE LOGITS
     trapped
    1.05
     stuck
    1.02
     caught
    0.97
     Stuck
    0.88
    ьаж
    0.85
    Stuck
    0.85
     stranded
    0.85
    stuck
    0.82
     kasarigan
    0.79
     atrap
    0.79
    Activations Density 2.444%

    No Known Activations