© 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. 9527
    Prev
    Next
    INDEX
    Explanations

    the word "thereof" and the word "each" along with capitalized words like "upper."

    oai_token-act-pair · gemini-2.0-flash

    thereof

    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
     AssemblyCompany
    -0.57
     />";
    -0.57
     joaat
    -0.54
    <bos>
    -0.54
    oa̍t
    -0.51
    lgari
    -0.50
    すと
    -0.50
    zusetzen
    -0.47
    MENAFN
    -0.47
    addComponent
    -0.47
    POSITIVE LOGITS
     ainfi
    0.68
    abestanden
    0.68
     auffi
    0.64
     Efq
    0.64
    ГЛА
    0.62
     poffible
    0.60
     prêtres
    0.60
     Gegenteil
    0.60
     Cæsar
    0.60
     himſelf
    0.60
    Activations Density 0.370%

    No Known Activations