© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15935
    Prev
    Next
    INDEX
    Explanations

    words that have a negative polarity and/or words related to numbers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    (...)
    -0.50
    browserify
    -0.49
    }{|
    -0.48
     selber
    -0.47
    forChild
    -0.45
    WireFormat
    -0.45
    …..
    -0.43
     disambiguazione
    -0.43
    ensement
    -0.43
    MigrationBuilder
    -0.43
    POSITIVE LOGITS
    ]--;
    0.68
     métallique
    0.63
    اریخ
    0.63
    BeginInit
    0.62
     CreateTagHelper
    0.61
     dirit
    0.60
     useAppContext
    0.60
    \{\\
    0.60
    httphttps
    0.59
     DbSet
    0.59
    Activations Density 5.710%

    No Known Activations