© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3210
    Prev
    Next
    INDEX
    Explanations

    words related to global business strategy and marketing, especially for large companies

    oai_token-act-pair · gemini-2.0-flash

    business expansion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     виправивши
    -0.68
     typelib
    -0.64
     propOrder
    -0.63
    IsMutable
    -0.52
    IMPORTED
    -0.50
    tanleria
    -0.49
    RTEE
    -0.49
    +#+
    -0.48
    ########.
    -0.47
     otomatig
    -0.47
    POSITIVE LOGITS
    URLException
    0.66
    이터
    0.56
     viewType
    0.55
     Efq
    0.53
    altes
    0.53
    неопр
    0.52
     تانيه
    0.51
    listdir
    0.51
     CURIAM
    0.50
    archiviato
    0.49
    Activations Density 17.762%

    No Known Activations