© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5634
    Prev
    Next
    INDEX
    Explanations

    words that often precede a noun

    oai_token-act-pair · gemini-2.0-flash

    specifications or descriptions

    np_max-act-logits · gemini-2.0-flash

    say "word-start" Method used: 2 — because all following tokens start with ▁, indicating word-start

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    GEBURTSDATUM
    -0.89
     computing
    -0.79
     fishing
    -0.77
     localVar
    -0.74
    ,:);
    -0.73
     సౌకర్య
    -0.71
     cooking
    -0.71
    computing
    -0.70
     Fishing
    -0.68
     programming
    -0.68
    POSITIVE LOGITS
    expandindo
    0.57
     kasarigan
    0.55
     مرئيه
    0.46
    
    0.46
     AssemblyCulture
    0.42
     démocr
    0.40
     verra
    0.39
    libft
    0.38
    請繼續往下閱讀
    0.38
    ########.
    0.38
    Activations Density 4.443%

    No Known Activations