© 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. 16122
    Prev
    Next
    INDEX
    Explanations

    language related to condemnation of international agreements

    oai_token-act-pair · gemini-2.0-flash

    North

    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
    Personendaten
    -0.60
     Aegean
    -0.59
     Assyrian
    -0.52
     Yerevan
    -0.49
     Serbian
    -0.49
     Davao
    -0.49
     Urugu
    -0.48
     Haitian
    -0.48
     Croatian
    -0.48
     propOrder
    -0.47
    POSITIVE LOGITS
     North
    1.08
    North
    1.00
     NORTH
    0.90
    NORTH
    0.80
    north
    0.74
    Amaz
    0.73
     north
    0.71
     Amaz
    0.70
     北
    0.68
     AssemblyProduct
    0.68
    Activations Density 1.297%

    No Known Activations