© 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. 5483
    Prev
    Next
    INDEX
    Explanations

    text relating to political accords and peace processes

    oai_token-act-pair · gemini-2.0-flash

    peace

    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
     Lordships
    -0.65
    BufferException
    -0.61
    ⓧ
    -0.59
     AssemblyCompany
    -0.54
    SizeMode
    -0.51
    aarrggbb
    -0.51
    __.__
    -0.50
    ItemBackground
    -0.50
    Добавлено
    -0.50
    MLLoader
    -0.49
    POSITIVE LOGITS
     peace
    1.50
    peace
    1.16
     Peace
    1.07
    Peace
    1.04
     PEACE
    1.02
    PEACE
    0.91
     paix
    0.87
     paz
    0.83
    antMatchers
    0.69
     broker
    0.68
    Activations Density 1.944%

    No Known Activations