© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15923
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "tags" or "boxes" in code

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Reſ
    -0.64
     Diſ
    -0.62
     Channel
    -0.59
     Anſ
    -0.59
     Secret
    -0.57
     Service
    -0.56
     Head
    -0.56
     Press
    -0.56
     Unit
    -0.56
     Paper
    -0.56
    POSITIVE LOGITS
    Посилання
    0.47
     sowas
    0.44
    Искәрмәләр
    0.42
    Metallica
    0.40
    Valencia
    0.40
    Източници
    0.39
     NgModule
    0.39
    Juventus
    0.39
    bardier
    0.39
    ionados
    0.38
    Activations Density 3.300%

    No Known Activations