© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10236
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings and law enforcement

    oai_token-act-pair · gemini-2.0-flash

    the term "office"

    np_token-act-pair-logits · gpt-4o-mini

    office

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     '\\;'
    -0.74
    chyma
    -0.58
    District
    -0.56
    Personendaten
    -0.55
     district
    -0.54
     District
    -0.52
     DISTRICT
    -0.51
    district
    -0.50
     }}"></
    -0.50
     Wiktionnaire
    -0.50
    POSITIVE LOGITS
     office
    1.22
     Office
    1.14
    Office
    1.05
    office
    1.02
     OFFICE
    1.02
     Offices
    0.96
    OFFICE
    0.92
     offices
    0.89
     oficina
    0.81
     Büro
    0.77
    Activations Density 2.939%

    No Known Activations