© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3666
    Prev
    Next
    INDEX
    Explanations

    legal or law-related terms

    oai_token-act-pair · gemini-2.0-flash

    legal arguments and evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    
    -0.47
     ALSO
    -0.42
    יב
    -0.41
    AllowAnonymous
    -0.40
    ABOVE
    -0.40
     kế
    -0.40
     Above
    -0.40
    >>
    -0.40
     ABOVE
    -0.38
     recht
    -0.38
    POSITIVE LOGITS
     препратки
    0.77
     pinulongan
    0.69
     itſelf
    0.65
    ThemeOverlay
    0.65
     ſeveral
    0.65
     juſt
    0.63
     moschino
    0.63
     Riproduzione
    0.63
     Argyle
    0.63
     Monfieur
    0.62
    Activations Density 2.978%

    No Known Activations