© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10879
    Prev
    Next
    INDEX
    Explanations

    terms related to software development, virtual machines, and cloud computing

    oai_token-act-pair · gemini-2.0-flash

    virtual machines and emulators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     balik
    -0.58
     Balik
    -0.54
    誉
    -0.52
     sumpay
    -0.48
     Regard
    -0.48
     griega
    -0.47
     referenties
    -0.47
    SequentialGroup
    -0.46
     rever
    -0.46
     regard
    -0.45
    POSITIVE LOGITS
    Bioaccumulative
    0.68
     Мексичка
    0.67
    __(/*!
    0.60
     BorderRadius
    0.59
    хьтан
    0.59
    Enllaces
    0.58
     defaultstate
    0.58
    ResumeLayout
    0.57
    ISupport
    0.56
     disponibilités
    0.55
    Activations Density 2.680%

    No Known Activations