© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1557
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to fantasy stories about princesses, kingdoms, and quests

    oai_token-act-pair · gemini-2.0-flash

    fantasy plots

    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
     يتيمه
    -0.65
    IVEREF
    -0.64
     تضيفلها
    -0.61
    impianto
    -0.55
    esterno
    -0.54
    mbros
    -0.54
    writeFieldEnd
    -0.52
     lccn
    -0.52
     חיצוניים
    -0.52
    }]
    -0.52
    POSITIVE LOGITS
     незавершена
    0.58
    Története
    0.54
    IndentedString
    0.51
    httphttps
    0.50
     poveznice
    0.49
     Murillo
    0.48
    FailureListener
    0.47
    stris
    0.47
    ühnen
    0.46
     StringTokenizer
    0.45
    Activations Density 2.549%

    No Known Activations