© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12334
    Prev
    Next
    INDEX
    Explanations

    phrases including "of all time," and mentions of time periods like "generation."

    oai_token-act-pair · gemini-2.0-flash

    all

    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
    Negative Logits
    providedIn
    -0.75
    InstrumentedTest
    -0.64
    #
    -0.59
     equipments
    -0.50
    minton
    -0.50
     numberOfRows
    -0.49
     Nowadays
    -0.49
     Soria
    -0.48
     initState
    -0.47
     чём
    -0.47
    POSITIVE LOGITS
    ukkah
    0.65
     hefyd
    0.65
     (£
    0.65
    FTFY
    0.63
    ագրություններ
    0.62
    AFFIRMED
    0.59
     calendriers
    0.59
    kohl
    0.58
     DialogResult
    0.58
     Vort
    0.58
    Activations Density 6.165%

    No Known Activations