© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11982
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "make sense"

    oai_token-act-pair · gemini-2.0-flash

    makes sense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    قایناق‌لار
    -0.63
    offsetof
    -0.61
    bootstrapcdn
    -0.60
    ViewFeatures
    -0.59
     unknownFields
    -0.57
    jsdelivr
    -0.56
    WriteTagHelper
    -0.56
     MAKE
    -0.51
    sofá
    -0.51
     GenerationType
    -0.50
    POSITIVE LOGITS
     degeneracy
    0.60
     createSprite
    0.52
     inertial
    0.52
     gesta
    0.51
     geologists
    0.50
     epidemiological
    0.50
    раздо
    0.50
    archiviato
    0.50
     lilies
    0.49
     Lining
    0.49
    Activations Density 3.041%

    No Known Activations