© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11941
    Prev
    Next
    INDEX
    Explanations

    the word "and" along with words occurring close to it

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     oprot
    -0.77
    StructEnd
    -0.76
    ftagPool
    -0.71
     TextAppearance
    -0.71
     @"/
    -0.70
     AssemblyProduct
    -0.67
    EndProject
    -0.66
     Roskov
    -0.64
     EconPapers
    -0.64
    httphttps
    -0.64
    POSITIVE LOGITS
     impunity
    0.47
    privilege
    0.38
    loh
    0.37
    ladel
    0.37
     privilege
    0.37
     success
    0.36
    alah
    0.36
     rechter
    0.36
     precedents
    0.35
     succès
    0.35
    Activations Density 2.765%

    No Known Activations