© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12225
    Prev
    Next
    INDEX
    Explanations

    transitional conclusion words, often used in legal or academic writing

    oai_token-act-pair · gemini-2.0-flash

    conclusions and logical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     snippetHide
    -0.76
     CreateTagHelper
    -0.61
    EndInit
    -0.61
     Efq
    -0.60
    Autoritní
    -0.59
     CURIAM
    -0.57
     shewn
    -0.57
     Vainqueur
    -0.55
     isKindOfClass
    -0.54
     LCCN
    -0.52
    POSITIVE LOGITS
     So
    0.82
    So
    0.75
     so
    0.71
     hence
    0.69
     therefore
    0.67
    so
    0.67
    SO
    0.66
     بنابراین
    0.66
     Donc
    0.66
    sprechend
    0.65
    Activations Density 1.290%

    No Known Activations