© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear often in scientific or technical writing, especially when referencing earlier work.

    oai_token-act-pair · gemini-2.0-flash

    previous

    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
     previous
    -1.15
    previous
    -1.09
     sebelumnya
    -1.04
     Previous
    -1.03
    Previous
    -0.95
     PREVIOUS
    -0.90
     предыду
    -0.85
     previously
    -0.84
    prev
    -0.82
     precedente
    -0.82
    POSITIVE LOGITS
     سكانية
    0.71
    (!__
    0.70
    chism
    0.69
     autorytatywna
    0.69
     EEC
    0.68
     CreateTagHelper
    0.68
    الإنجليزية
    0.67
    parsedMessage
    0.66
    actionMode
    0.66
    Composable
    0.66
    Activations Density 33.922%

    No Known Activations