© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13366
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific or legal writing.

    oai_token-act-pair · gemini-2.0-flash

    academic/research writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     виправивши
    -0.93
    DeleteBehavior
    -0.84
    PerformLayout
    -0.77
     AssemblyTitle
    -0.74
     Italijanski
    -0.73
    Datuak
    -0.73
    تقاوى
    -0.69
    ///</
    -0.69
    Хьажоргаш
    -0.69
     مشين
    -0.68
    POSITIVE LOGITS
    dingen
    0.43
     Fu
    0.43
     or
    0.43
     building
    0.41
     resident
    0.41
     convinced
    0.41
     free
    0.41
    必
    0.41
    ja
    0.40
    klá
    0.40
    Activations Density 22.148%

    No Known Activations