© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5842
    Prev
    Next
    INDEX
    Explanations

    words frequently used in legal documents with special emphasis on names and titles

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ExecuteAsync
    -0.59
    ็จ
    -0.55
     JIM
    -0.53
     mike
    -0.53
     Insee
    -0.52
    SqlClient
    -0.51
    Mike
    -0.50
     Mick
    -0.50
     Pete
    -0.50
    Referencias
    -0.49
    POSITIVE LOGITS
     William
    1.16
     Thomas
    1.16
     Edward
    1.11
     James
    1.09
    Thomas
    1.05
     Joseph
    1.04
     Timothy
    1.02
     Daniel
    1.02
    William
    1.02
     Ronald
    1.01
    Activations Density 3.886%

    No Known Activations