© 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. 15613
    Prev
    Next
    INDEX
    Explanations

    research publications including author names and university details

    oai_token-act-pair · gemini-2.0-flash

    non-English or technical syntactic constructs

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

    code and names

    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
    insee
    -0.62
    最快更新
    -0.48
    MethodImpl
    -0.47
    มาะ
    -0.46
     Solid
    -0.45
     continúas
    -0.45
     Self
    -0.44
     Commencez
    -0.43
     ligiloj
    -0.43
    Comté
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.77
     MainAxisSize
    0.59
    сла
    0.57
    sweise
    0.54
    fern
    0.54
    +#+#
    0.52
    ミナル
    0.50
    WriteTagHelper
    0.50
     للاسماء
    0.50
     FetchType
    0.49
    Activations Density 0.602%

    No Known Activations