© 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. 14952
    Prev
    Next
    INDEX
    Explanations

    phrases describing enhancements or additions

    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
     bunch
    -1.29
    Bunch
    -1.05
    bunch
    -1.04
     Bunch
    -0.95
     bunches
    -0.80
     cherchés
    -0.76
     Anſ
    -0.75
     anſ
    -0.74
     الدولى
    -0.74
     autorytatywna
    -0.73
    POSITIVE LOGITS
     something
    1.38
    something
    1.29
    Something
    1.11
     Something
    1.09
     SOMETHING
    0.99
     algo
    0.88
     quelque
    0.80
     qualcosa
    0.79
    someone
    0.77
     someone
    0.73
    Activations Density 2.426%

    No Known Activations