© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14946
    Prev
    Next
    INDEX
    Explanations

    text that contains the word "than" used for comparisons

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     uovo
    -0.43
    middels
    -0.41
     vicenda
    -0.40
     lieux
    -0.38
    лович
    -0.38
     faixa
    -0.36
     cervello
    -0.36
     händ
    -0.36
     autorité
    -0.36
     namanya
    -0.36
    POSITIVE LOGITS
     sending
    1.34
     agreeing
    1.30
     pushing
    1.30
     releasing
    1.29
     letting
    1.29
     giving
    1.29
     adding
    1.28
     displaying
    1.28
     calling
    1.27
     picking
    1.27
    Activations Density 10.448%

    No Known Activations