© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4722
    Prev
    Next
    INDEX
    Explanations

    words associated with promotional material, especially related to services, locations and real estate

    oai_token-act-pair · gemini-2.0-flash

    Web page context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.56
     Spisak
    -0.51
    gonic
    -0.51
     hashed
    -0.50
    etted
    -0.49
    TryParse
    -0.48
     '\\;'
    -0.48
     paternity
    -0.47
     AssemblyProduct
    -0.47
     homology
    -0.46
    POSITIVE LOGITS
    awtextra
    0.62
     البيانات
    0.51
    tvguidetime
    0.50
    Izvori
    0.50
     extra
    0.49
     rechange
    0.48
    brtc
    0.47
    ResourceManager
    0.46
    RTEE
    0.46
    Lähteet
    0.46
    Activations Density 2.101%

    No Known Activations