© 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. 15752
    Prev
    Next
    INDEX
    Explanations

    the verb "open" in encouraging, metaphorical, or philosophical contexts

    oai_token-act-pair · gemini-2.0-flash

    open

    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
    Datuak
    -0.64
    principalTable
    -0.58
    isOpen
    -0.56
    GenerationType
    -0.54
    Jeografia
    -0.49
    tagext
    -0.48
     abertura
    -0.48
     rempliss
    -0.48
     hoist
    -0.47
    apertura
    -0.47
    POSITIVE LOGITS
    ChromeDriver
    0.59
    Kjelder
    0.59
    FTFY
    0.57
    MemoryWarning
    0.55
    setupUi
    0.53
    testify
    0.53
    الدراسه
    0.51
    AutoScaleMode
    0.50
    migrationBuilder
    0.50
    ViewGroup
    0.50
    Activations Density 3.826%

    No Known Activations