© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9558
    Prev
    Next
    INDEX
    Explanations

    legal documents and international relations, particularly those involving the treatment of prisoners of war and conventions.

    oai_token-act-pair · gemini-2.0-flash

    international agreements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     cauſe
    -0.56
    出版年
    -0.56
    couvrez
    -0.52
    tanleria
    -0.52
     Jefus
    -0.51
     reaſon
    -0.50
    Locality
    -0.50
     nôtre
    -0.49
    Izvori
    -0.49
     становника
    -0.49
    POSITIVE LOGITS
     Convention
    1.14
     convention
    1.14
     conventions
    1.09
    Convention
    1.02
    convention
    0.98
     Conventions
    0.98
     signed
    0.90
     signing
    0.89
     ratification
    0.85
     ratified
    0.84
    Activations Density 0.868%

    No Known Activations