© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3254
    Prev
    Next
    INDEX
    Explanations

    words and phrases where the author makes a recommendation to the reader, urging them to take some particular action.

    oai_token-act-pair · gemini-2.0-flash

    patterns starting with 'you' followed by verbs or commands

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

    action encouragement

    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
    Negative Logits
    DockStyle
    -1.03
     المعيارى
    -1.03
    expandindo
    -0.98
    WriteTagHelper
    -0.94
     Efq
    -0.91
     unknownFields
    -0.87
     Eſ
    -0.87
     whoſe
    -0.86
     ویکی‌آمباردا
    -0.85
     becauſe
    -0.84
    POSITIVE LOGITS
     head
    0.50
     per
    0.49
     del
    0.39
     pl
    0.38
     fon
    0.38
    uc
    0.37
     pu
    0.37
     S
    0.37
    <eos>
    0.36
    冲
    0.36
    Activations Density 0.890%

    No Known Activations