© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6742
    Prev
    Next
    INDEX
    Explanations

    language related to the regulation of business practices.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "raise"

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

    raise

    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
     صوتيه
    -0.62
    RenderAtEndOf
    -0.56
    Autoritní
    -0.54
     Paglinawan
    -0.52
     coel
    -0.51
    BeginContext
    -0.50
    ibatis
    -0.49
     estiver
    -0.49
    ByPrimaryKey
    -0.48
     ſtate
    -0.48
    POSITIVE LOGITS
     raises
    1.25
     raise
    1.23
    raise
    1.17
     Raise
    1.09
     raised
    1.08
     Raises
    1.06
    Raise
    1.06
     raising
    1.03
    Raising
    0.95
    raises
    0.92
    Activations Density 2.246%

    No Known Activations