© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5308
    Prev
    Next
    INDEX
    Explanations

    words related to production, advertising, graphic design and film-making

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "agency"

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

    agency

    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
    apunov
    -0.54
    nbar
    -0.52
    urals
    -0.50
    )))));
    -0.49
    WriteTagHelper
    -0.48
    ári
    -0.47
    pilot
    -0.46
    farin
    -0.46
    anneer
    -0.44
    र्जा
    -0.44
    POSITIVE LOGITS
     agency
    1.68
     agencies
    1.48
     Agency
    1.41
    agency
    1.39
    Agency
    1.38
     AGENCY
    1.34
     Agencies
    1.30
     agencia
    1.23
    Agencies
    1.22
     agence
    1.20
    Activations Density 1.494%

    No Known Activations