© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12736
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    technical documentation/code

    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
     gavetas
    -0.53
    TestingModule
    -0.53
     tänka
    -0.52
     denke
    -0.51
     Sociale
    -0.50
     dieux
    -0.49
     azon
    -0.49
     dommages
    -0.49
     verticales
    -0.49
     cumbre
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.81
     >=",
    0.77
     AssemblyTitle
    0.71
    出版年
    0.69
     Италијани
    0.68
    basicConfig
    0.66
    جستارهای
    0.65
    ]")]
    0.63
    keyColumn
    0.61
    felves
    0.59
    Activations Density 1.431%

    No Known Activations