© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 15802
    Prev
    Next
    INDEX
    Explanations

    mentions of online retail, especially pharmaceuticals and VPN proxies

    oai_token-act-pair · gemini-2.0-flash

    online services and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     pazar
    -0.50
     pará
    -0.46
     leksikon
    -0.45
     old
    -0.42
     round
    -0.42
    ccia
    -0.42
     messenger
    -0.42
     Muddy
    -0.42
    thys
    -0.42
     pasaran
    -0.42
    POSITIVE LOGITS
     utafitiHapana
    0.74
    adaptiveStyles
    0.71
     estekak
    0.70
    CppCodeGen
    0.65
     مرئيه
    0.64
     linkovi
    0.60
     initComponents
    0.60
    AndEndTag
    0.59
    staticmethod
    0.58
     AssemblyCulture
    0.57
    Activations Density 0.436%

    No Known Activations