© 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. 3561
    Prev
    Next
    INDEX
    Explanations

    the word "body" when it's followed by a word relating to a creative or political "work"

    oai_token-act-pair · gemini-2.0-flash

    body

    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
     Crom
    -0.54
    EndGlobalSection
    -0.50
    thenia
    -0.49
     урна
    -0.49
     صوتيه
    -0.48
    ดุ
    -0.46
    WebElementEntity
    -0.46
    disambiguation
    -0.46
    odic
    -0.46
     közé
    -0.45
    POSITIVE LOGITS
    getMenuInflater
    0.57
     AssemblyCulture
    0.57
    ьаж
    0.56
     يتيمه
    0.52
     esternos
    0.52
    зулта
    0.52
    inflate
    0.51
    IntoConstraints
    0.51
     GenerationType
    0.50
     Arrondissement
    0.50
    Activations Density 6.661%

    No Known Activations