© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11180
    Prev
    Next
    INDEX
    Explanations

    words associated with government bodies and administrative structures

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    abs
    -0.45
     espada
    -0.42
    fs
    -0.41
    Campbell
    -0.40
     basa
    -0.39
    <eos>
    -0.39
    Clifford
    -0.39
    offsetof
    -0.39
    ABS
    -0.38
    Ahh
    -0.37
    POSITIVE LOGITS
    ]--;
    0.73
    adpleegd
    0.69
     חיצוניים
    0.67
    ficulty
    0.65
    iffance
    0.64
    )";
    0.63
     فريبيس
    0.63
    iedenen
    0.62
    脚注の使い方
    0.61
    ftagPool
    0.61
    Activations Density 0.889%

    No Known Activations