© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6927
    Prev
    Next
    INDEX
    Explanations

    sections of technical writing, particularly about data analysis, that discuss how algorithms are performing

    oai_token-act-pair · gemini-2.0-flash

    results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    expandindo
    -0.61
    fjspx
    -0.60
     velkommen
    -0.57
     صوتيه
    -0.57
    URLException
    -0.56
     defaultstate
    -0.55
    =$?
    -0.54
     "));
    -0.53
    wpa
    -0.53
    saraba
    -0.53
    POSITIVE LOGITS
     results
    1.23
    Results
    1.10
    results
    1.09
     Results
    1.09
     RESULTS
    1.05
    RESULTS
    0.98
     resultados
    0.98
     Ergebnisse
    0.94
     result
    0.91
     résultats
    0.88
    Activations Density 1.905%

    No Known Activations