© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2140
    Prev
    Next
    INDEX
    Explanations

    words related to relationships set in the context of books and storytelling.

    oai_token-act-pair · gemini-2.0-flash

    terms related to storytelling and complex narratives

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

    Stories

    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
    tvguidetime
    -0.54
     démocr
    -0.52
     fidèles
    -0.50
    出版年
    -0.50
     déclar
    -0.50
    orteur
    -0.48
    \{\\
    -0.48
    şekkür
    -0.47
     aéri
    -0.47
     opérateur
    -0.47
    POSITIVE LOGITS
    Portale
    0.68
    MessageTagHelper
    0.66
    sizeCache
    0.62
    SourceChecksum
    0.59
    titleMargin
    0.59
     breaking
    0.57
     break
    0.57
     disambiguazione
    0.56
    Personensuche
    0.54
     fate
    0.54
    Activations Density 7.126%

    No Known Activations