© 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. 13304
    Prev
    Next
    INDEX
    Explanations

    content from request forms, prison interactions, or customer service inquiries.

    oai_token-act-pair · gemini-2.0-flash

    said or told

    np_max-act-logits · gemini-2.0-flash

    tokens related to requests or actions

    np_token-act-pair-logits · gpt-4o-mini
    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
     ſever
    -0.65
     pleaſure
    -0.65
     raiſ
    -0.65
     SIA
    -0.62
     neceffary
    -0.62
     mathematicians
    -0.60
     neceſſ
    -0.60
     المعيارى
    -0.59
     deſt
    -0.58
     itſelf
    -0.57
    POSITIVE LOGITS
     my
    0.62
     Савезне
    0.55
    IsContent
    0.54
    invokeLater
    0.52
     me
    0.51
    PerformLayout
    0.50
     发表于
    0.50
    +#+#
    0.50
    TagHelper
    0.49
    endpush
    0.49
    Activations Density 6.573%

    No Known Activations