© 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. 1747
    Prev
    Next
    INDEX
    Explanations

    descriptive words used in storytelling, especially words evoking a sense of unease or the surreal.

    oai_token-act-pair · gemini-2.0-flash

    tokens associated with programming or technical terms

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

    Descriptive language

    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
     lourd
    -0.62
     aveug
    -0.62
     enfans
    -0.60
     déchir
    -0.59
     feroit
    -0.59
     becauſe
    -0.59
     élevés
    -0.58
     rempliss
    -0.57
     traités
    -0.57
    GraphicsUnit
    -0.57
    POSITIVE LOGITS
    ,
    0.60
    ArgumentParser
    0.56
     corners
    0.56
    AnchorStyles
    0.54
     disposition
    0.54
     protoimpl
    0.52
     فريبيس
    0.52
    كويكب
    0.51
     cherchés
    0.51
     goodness
    0.51
    Activations Density 3.372%

    No Known Activations