© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11407
    Prev
    Next
    INDEX
    Explanations

    words related to copyright law

    oai_token-act-pair · gemini-2.0-flash

    copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     itſelf
    -0.94
     Copyright
    -0.86
    zzleHttp
    -0.85
     copyright
    -0.84
    UserScript
    -0.81
    noons
    -0.79
     themſelves
    -0.78
     Theſe
    -0.77
     BoxFit
    -0.77
     purpoſe
    -0.77
    POSITIVE LOGITS
    <bos>
    0.69
    الإنجليزية
    0.51
     e
    0.39
    脚注の使い方
    0.38
    hoot
    0.38
     r
    0.36
     E
    0.36
     branch
    0.35
     посте
    0.35
    Становништво
    0.35
    Activations Density 9.495%

    No Known Activations