© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8756
    Prev
    Next
    INDEX
    Explanations

    instances of people reading, listening, or being quiet to each other

    oai_token-act-pair · gemini-2.0-flash

    Listening or voice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RenderAtEndOf
    -0.64
    principalTable
    -0.59
     AssemblyTitle
    -0.57
    aarrggbb
    -0.55
    ()?;
    -0.55
     Monfieur
    -0.55
    contentLoaded
    -0.54
    Rüyada
    -0.53
     aapt
    -0.52
    detectChanges
    -0.52
    POSITIVE LOGITS
    intahan
    0.60
    ướp
    0.47
    ViewImports
    0.47
     gespannt
    0.47
    OCCURRED
    0.46
    脚注の使い方
    0.46
    ressible
    0.45
     certiorari
    0.44
    ichio
    0.43
     viewDidLoad
    0.43
    Activations Density 0.260%

    No Known Activations