© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 432
    Prev
    Next
    INDEX
    Explanations

    the beginning of a numbered list

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
    Negative Logits
    _
    -0.65
     thon
    -0.62
     Grind
    -0.51
    NUMX
    -0.51
    ····
    -0.50
     NEA
    -0.49
    ······
    -0.49
     Facial
    -0.49
     auras
    -0.48
    anar
    -0.48
    POSITIVE LOGITS
    <bos>
    1.27
    complexType
    0.73
     للمعارف
    0.70
     beginnetje
    0.67
    ագրություններ
    0.66
     дописавши
    0.65
     himo
    0.62
    nologue
    0.62
     '\\;'
    0.61
    EndGlobalSection
    0.61
    Activations Density 2.139%

    No Known Activations