© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5976
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with comparisons and research findings, often in academic or technical contexts

    oai_token-act-pair · gemini-2.0-flash

    quantities

    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
     оригіналу
    -0.71
    MENAFN
    -0.63
     Référence
    -0.57
    platin
    -0.56
    <?
    -0.53
    ("-");
    -0.52
    ionales
    -0.50
     صوتيه
    -0.50
     Kis
    -0.50
     ioutil
    -0.49
    POSITIVE LOGITS
     considerably
    0.99
     significantly
    0.93
     twice
    0.89
     much
    0.86
     substantially
    0.85
    significantly
    0.83
     znacznie
    0.79
     doppelt
    0.79
     намного
    0.78
    much
    0.75
    Activations Density 2.155%

    No Known Activations