© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13107
    Prev
    Next
    INDEX
    Explanations

    discussions about hardware switches, particularly related to disabling devices like Wi-Fi or microphones.

    oai_token-act-pair · gemini-2.0-flash

    Computer hardware context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    feira
    -0.54
     Z
    -0.49
     lettere
    -0.47
    人心
    -0.46
    useEffect
    -0.46
     رو
    -0.46
    ÇO
    -0.46
    GRANTED
    -0.45
    //
    -0.45
    ква
    -0.45
    POSITIVE LOGITS
    ">//
    0.63
    ViewFeatures
    0.61
    ThroughAttribute
    0.59
     Theſe
    0.55
     parseFrom
    0.55
    liputi
    0.54
     />\
    0.54
     ſmall
    0.54
     &___
    0.54
     zewnętrzne
    0.54
    Activations Density 1.216%

    No Known Activations