© 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. 2739
    Prev
    Next
    INDEX
    Explanations

    words related to the economics of the internet, business and tech

    oai_token-act-pair · gemini-2.0-flash

    Business platforms, Amazon

    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
    WriteLiteral
    -0.55
    tudiant
    -0.41
    bukkit
    -0.40
    ronom
    -0.39
     computa
    -0.39
    Wirk
    -0.39
     memen
    -0.38
    ModelState
    -0.37
    PhysRev
    -0.37
    ضو
    -0.36
    POSITIVE LOGITS
     مرئيه
    0.92
     AssemblyCulture
    0.87
     дописавши
    0.83
     '\\;'
    0.83
     >=",
    0.70
    DOCTYPE
    0.69
     ویکی‌پدی
    0.66
    tagHelperRunner
    0.66
    Cyfarwyddwr
    0.65
    AutoresizingMask
    0.65
    Activations Density 2.154%

    No Known Activations