© 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. 15050
    Prev
    Next
    INDEX
    Explanations

    words related to PDF readers and documents

    oai_token-act-pair · gemini-2.0-flash

    reader

    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
     iprot
    -0.58
    Strut
    -0.53
    SqlClient
    -0.53
     utafitiHapana
    -0.53
     SqlCommand
    -0.50
    RequestBody
    -0.49
     SECRET
    -0.48
    Nib
    -0.48
    ecma
    -0.48
    Jsp
    -0.48
    POSITIVE LOGITS
     unknownFields
    0.79
    AsUp
    0.76
     pinulongan
    0.66
    ItemBackground
    0.66
     Audiodateien
    0.65
    Datuak
    0.60
    Билгалдахарш
    0.58
    BeginInit
    0.57
     وتسجيلات
    0.56
    🏻‍♀️
    0.55
    Activations Density 1.085%

    No Known Activations