© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3784
    Prev
    Next
    INDEX
    Explanations

    references to things at the top

    oai_token-act-pair · gemini-2.0-flash

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     top
    -2.77
    Top
    -2.41
    top
    -2.39
     Top
    -2.28
     TOP
    -2.08
    TOP
    -2.03
     tops
    -1.77
    トップ
    -1.71
    tops
    -1.66
     topp
    -1.59
    POSITIVE LOGITS
    webElementGuid
    0.57
    bibinfo
    0.50
    TryParse
    0.49
    citep
    0.46
    AILS
    0.44
     niệm
    0.43
     hưởng
    0.43
     betreft
    0.42
    flexDirection
    0.42
     Suara
    0.42
    Activations Density 0.511%

    No Known Activations