© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13038
    Prev
    Next
    INDEX
    Explanations

    mentions of institutions such as government or medical buildings

    oai_token-act-pair · gemini-2.0-flash

    buildings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     magasiner
    -0.38
     JButton
    -0.33
     pangs
    -0.33
     >::
    -0.31
    easily
    -0.31
    atguigu
    -0.31
     adipis
    -0.31
    Risk
    -0.30
    forKey
    -0.30
    mmä
    -0.29
    POSITIVE LOGITS
    twimg
    0.85
     invokingState
    0.82
     يتيمه
    0.73
     ویکی‌پدیا
    0.72
    sizeCache
    0.71
    حوالہ
    0.71
    Gweler
    0.70
    principalTable
    0.69
     ostavi
    0.68
     للتو
    0.68
    Activations Density 11.823%

    No Known Activations