© 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
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15596
    Prev
    Next
    INDEX
    Explanations

    words related to people and their professional activities, possibly with an emphasis on financial or investment contexts

    oai_token-act-pair · gemini-2.0-flash

    oria

    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
     AssemblyTitle
    -0.68
    الإنجليزية
    -0.64
    ItemBackground
    -0.63
     getRule
    -0.63
    Życiorys
    -0.61
    :✨
    -0.60
     ролях
    -0.59
     uintptr
    -0.59
    OrBuilder
    -0.58
    toMatchSnapshot
    -0.58
    POSITIVE LOGITS
    TagMode
    0.65
    osk
    0.47
    गर
    0.43
    os
    0.42
     beats
    0.42
    roc
    0.41
    pered
    0.41
    hod
    0.41
    ecer
    0.41
    中部
    0.40
    Activations Density 37.601%

    No Known Activations