© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9174
    Prev
    Next
    INDEX
    Explanations

    references to numerical measurements of temperature, especially in Celsius

    oai_token-act-pair · gemini-2.0-flash

    technical terms and measurements

    np_token-act-pair-logits · gpt-4o-mini

    temperatures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     at
    -0.78
     Meksiku
    -0.64
     At
    -0.52
    Бахар
    -0.49
     الرياضيه
    -0.48
     AssemblyCulture
    -0.47
    mannian
    -0.47
    Ifc
    -0.46
    addCriterion
    -0.45
     QtCore
    -0.45
    POSITIVE LOGITS
    تقاوى
    0.76
    Skocz
    0.67
     legitimacy
    0.56
    Revenir
    0.53
    Datuak
    0.52
    liesslich
    0.52
     TMC
    0.52
    visibility
    0.51
    Salta
    0.51
    ReusableCell
    0.50
    Activations Density 0.814%

    No Known Activations