© 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. 16090
    Prev
    Next
    INDEX
    Explanations

    language typical of legal documents and court proceedings.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     G
    -0.49
    #
    -0.46
     in
    -0.46
     a
    -0.46
     an
    -0.46
    ,
    -0.46
     
    -0.45
    /
    -0.42
     on
    -0.42
     to
    -0.42
    POSITIVE LOGITS
    存于互联网档案馆
    1.17
     pleaſure
    1.13
     myſelf
    1.09
     виправивши
    1.07
     purpoſe
    1.02
     Efq
    1.02
     nahilalakip
    1.01
    脚注の使い方
    1.01
     تانيه
    1.00
     ―――――
    0.99
    Activations Density 4.107%

    No Known Activations