© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9504
    Prev
    Next
    INDEX
    Explanations

    uses of the words "high" and "low" in a technical context

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     higher
    -2.69
    Higher
    -2.58
    higher
    -2.56
     Higher
    -2.44
     HIGHER
    -2.28
     höheren
    -1.53
     höher
    -1.52
     lowest
    -1.52
     höhere
    -1.50
     hoger
    -1.46
    POSITIVE LOGITS
    المكان
    0.45
     препратки
    0.41
     manos
    0.40
    válasz
    0.40
    ילה
    0.40
    ucid
    0.40
    wpi
    0.40
    **/
    0.40
    ()]);
    0.40
    LEY
    0.40
    Activations Density 8.481%

    No Known Activations