© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4278
    Prev
    Next
    INDEX
    Explanations

    words related to writing styles and writers, especially related to books

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     script
    -0.60
     Performing
    -0.55
     stories
    -0.49
     scénario
    -0.49
     SCRIPT
    -0.48
     historias
    -0.48
     scrit
    -0.48
     scripts
    -0.47
     scrip
    -0.47
    tamaan
    -0.46
    POSITIVE LOGITS
    存于互联网档案馆
    0.84
     Савезне
    0.71
    GEBURTSDATUM
    0.69
     חיצוניים
    0.68
     mergeFrom
    0.67
    endregion
    0.66
     Efq
    0.66
    原始内容存档于
    0.65
    __':
    0.65
     oprot
    0.64
    Activations Density 3.854%

    No Known Activations