© 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. 4977
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    cross

    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
     results
    -0.97
     Results
    -0.87
    Results
    -0.82
    results
    -0.80
     RESULTS
    -0.76
     resultados
    -0.67
     résultats
    -0.66
    RESULTS
    -0.64
    resultados
    -0.63
    结果
    -0.63
    POSITIVE LOGITS
    cross
    0.85
    Cross
    0.84
     cross
    0.80
     Cross
    0.76
     crossed
    0.73
    CROSS
    0.69
     crosses
    0.66
    AxisAlignment
    0.63
     CROSS
    0.63
    CppMethod
    0.59
    Activations Density 2.005%

    No Known Activations