© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4176
    Prev
    Next
    INDEX
    Explanations

    numbers and ratios often used to describe the concentration of a substance

    oai_token-act-pair · gemini-2.0-flash

    numeric values and percentages

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

    1

    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
    homonymie
    -0.92
    rungsseite
    -0.89
     disambiguazione
    -0.74
    Tikang
    -0.68
    CppMethod
    -0.67
     betweenstory
    -0.66
    ValueStyle
    -0.66
     PublicKey
    -0.65
    تقاوى
    -0.65
    MemoryWarning
    -0.64
    POSITIVE LOGITS
     percent
    0.50
    %
    0.47
    ParallelGroup
    0.46
     Percent
    0.45
     out
    0.43
    neath
    0.42
     étrangère
    0.42
     untere
    0.41
     serpiente
    0.41
     tắt
    0.40
    Activations Density 2.847%

    No Known Activations