© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14708
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to positive emotions and experiences.

    oai_token-act-pair · gemini-2.0-flash

    positive emotions

    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
    abestanden
    -0.61
     Anſ
    -0.60
    ✭✭
    -0.59
     AssemblyCulture
    -0.59
     transfieras
    -0.56
    ArrowToggle
    -0.55
     himo
    -0.55
    OGND
    -0.54
    tagHelperRunner
    -0.52
     समीक्षाओं
    -0.52
    POSITIVE LOGITS
     and
    0.59
    Enders
    0.58
     in
    0.55
    setViewName
    0.55
    apunov
    0.52
    IActionResult
    0.52
    basicConfig
    0.52
    yarnpkg
    0.52
    ophanes
    0.51
    ":[{
    0.50
    Activations Density 6.986%

    No Known Activations