© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3148
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express positive sentiment or evaluation

    oai_token-act-pair · gemini-2.0-flash

    encouragement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    -0.64
    GeneratedMessage
    -0.61
     CWE
    -0.58
     المعيارى
    -0.57
    withIdentifier
    -0.56
    ſelf
    -0.53
     myſelf
    -0.52
     ebooks
    -0.51
    /***/
    -0.50
    وذ
    -0.49
    POSITIVE LOGITS
     contre
    0.53
    nesc
    0.50
     jakości
    0.50
     NUKAT
    0.48
     concetto
    0.47
     качество
    0.47
    namental
    0.46
    lorette
    0.46
     kötü
    0.46
    ///</
    0.46
    Activations Density 3.898%

    No Known Activations